ChatGPT | Dr. Mauricio Zambrano-Bigiarini

How to use ChatGPT to learn Hydrology - Part I: configuration, context and useful prompts

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading and practice time: 15-25 minutes.

Why this series of tutorials?

Preparing university students today for their future professional practice is unusually challenging because we cannot know precisely what Artificial Intelligence systems will be able to do in a few years. The capabilities of generative models are evolving rapidly, barriers to access are falling, and the range of tasks that can be automated is changing. Teaching only how to operate the current version of ChatGPT therefore has limited long-term value: the tools will change, but engineers will still need to understand a problem, judge the quality of an answer, verify evidence, detect errors and make responsible decisions.

Recent discussion in higher education points in the same direction. AI can broaden access to explanations, feedback and personalised learning, but it can also foster dependence, superficial learning and reduced exercise of critical thinking when it replaces the student’s own cognitive effort ( ). The challenge is therefore not simply to adopt AI more quickly, but to decide what it should be used for and what kind of learning we want it to support ( ). Likewise, recent analyses argue that higher education should strengthen capacities such as critical thinking, adaptability, curiosity and lifelong learning ( ), and that many of the decisions posed by AI are fundamentally pedagogical before they are technological ( ).

For that reason, the purpose of this three-part series is not to teach you how to obtain answers more quickly. It is to help you use generative AI to understand Hydrology more deeply, practise more effectively, identify what you still do not understand, and develop the autonomy required to solve unfamiliar problems. In short:

Use AI to increase learning, not to avoid the process of learning.

ChatGPT can help you learn Hydrology, or it can help you avoid learning it. The difference depends mainly on how you use it.

In IIO422-Hydrology, obtaining the correct numerical answer is not enough. The course expects you to analyse hydrological processes, quantify variables, work probabilistically, interpret results, detect errors and justify engineering decisions. Generative AI is explicitly permitted as a learning and computational support tool outside assessments, but its use must be critical, verifiable, transparent and responsible.

1. The fundamental rule: tutor, not autopilot

A weak query would be:

Explain the water balance.

A much better one would be:

I am taking IIO422-Hydrology in Civil Engineering.

I understand precipitation and streamflow, but I still confuse
evapotranspiration with changes in catchment storage.

Help me interpret the annual water balance physically.
First ask me two diagnostic questions.
Then correct my misconceptions and only afterwards give
a concise explanation.

Use units of mm/year and do not assume Delta S = 0
unless you justify that approximation.

The difference is not cosmetic. The second prompt forces you to think before receiving the explanation.

2. Configure the context that actually matters

The course assumes previous knowledge of Fluid Mechanics, Hydraulics, Statistics and English. It also requires you to collect and analyse hydrometeorological information, construct simplified water balances, perform frequency analysis, and estimate design rainfall and streamflow.

In Settings > Personalization > Custom Instructions, you could write:

I am a Civil Engineering student in Chile taking IIO422-Hydrology.

I have already passed Fluid Mechanics, Hydraulics and Statistics.
I also know how to program in R.

When helping me:
- prioritise reasoning and physical interpretation;
- use SI units;
- check dimensional consistency;
- distinguish data, assumptions, method, result and uncertainty;
- use examples from Chilean catchments when useful;
- do not invent data, references, packages or functions;
- if important information is missing, ask before assuming;
- for R, avoid tidyverse and prioritise base R, hydroTSM
 and the tools specified in the course;
- when I am preparing for an assessment, do not provide
 the full solution before I have attempted the problem.

Do not include personal information that is irrelevant to learning.

3. Connect ChatGPT with the Learning Outcomes

The syllabus defines five Learning Outcomes. Use them as a test of whether an AI interaction is actually helping you learn:

LO1: conceptually analyse key hydrological-cycle processes and apply them to Chilean catchments.
LO2: quantify the temporal evolution of precipitation, evapotranspiration and runoff using in-situ and gridded data.
LO3: analyse hydrological variables probabilistically for engineering design and planning.
LO4: incorporate social responsibility into water-resources management problems.
LO5: develop personal and teamwork skills needed to meet agreed objectives and deadlines.

A useful ChatGPT session should strengthen at least one of these outcomes. If it merely produces text or code that you cannot explain, it probably strengthens none of them.

4. The anatomy of a good prompt

For most course tasks, five components are sufficient:

ROLE + CONTEXT + TASK + CONSTRAINTS + OUTPUT

Role

Act as a university Hydrology lecturer for Civil Engineering.

Context

I am studying infiltration and the Green-Ampt method.
I understand infiltration capacity, but not the role
of initial soil moisture.

Task

Help me compare the same storm over an initially dry soil
and an initially wet soil.

Constraints

Do not invent parameter values.
Use SI units.
Do not simplify the assumptions of Green-Ampt without stating them.

Output

Answer in five parts:
1. physical idea;
2. relevant variables;
3. equation;
4. example;
5. one question to test my understanding.

5. Make the model recognise missing information

A hydrological answer may depend on:

temporal scale;
catchment area;
data resolution;
hydrological year;
antecedent conditions;
rainfall- or snow-dominated regime;
regulation;
units;
availability and quality of observations.

Add:

Before solving the problem, identify whether essential information
is missing.

If it is, ask me no more than three specific questions.
Do not introduce silent assumptions.

6. Use the course learning sequence as a dialogue structure

The syllabus organises learning around:

conceptualisation
→ application
→ evidence analysis
→ perturbation of the problem
→ interpretation
→ defence of results

You can turn that sequence directly into a prompt:

I want to study [TOPIC].

Work with me in six stages:
1. conceptualisation;
2. application;
3. evidence;
4. change one assumption or input;
5. ask me to interpret what changes;
6. make me defend the conclusion.

This is more useful than requesting a long explanation.

7. Separate facts, assumptions, results and uncertainty

For quantitative problems:

Separate your response into:
- available data;
- assumptions;
- equations;
- calculation;
- result;
- physical interpretation;
- uncertainty;
- limitations.

This mirrors the course-wide assessment criteria: conceptual understanding, mathematical correctness, dimensional consistency, hydrological reasoning, physical interpretation, critical judgement and consideration of uncertainty.

8. Fluency does not imply truth

ChatGPT can produce polished but incorrect answers.

Watch especially for:

unit errors;
incorrect signs;
mixed temporal scales;
confusion between exceedance and non-exceedance;
methods used outside their assumptions;
fabricated data;
non-existent references;
non-existent R functions;
causal interpretations unsupported by evidence.

Try:

Audit your answer.

Look specifically for:
1. conceptual errors;
2. dimensional errors;
3. unstated assumptions;
4. physically implausible results;
5. omitted uncertainty;
6. references or functions you cannot verify.

9. AI is not a scientific authority

The syllabus is explicit: AI tools do not replace hydrological analysis and are not sources of scientific authority.

Verify important information using:

course material;
textbooks;
scientific papers;
official documentation;
R documentation;
original data;
independent calculations;
physical-consistency checks.

10. Declare AI use in practical assignments

Each practical assignment should include a brief declaration identifying at least:

tool used;
purpose;
component in which it was used;
verification procedure.

For example:

Tool: ChatGPT.
Purpose: support in debugging an R function for temporal aggregation.
Component: script 02_hydroclimate.R.
Verification: comparison with an independent calculation,
unit checks and consultation of the hydroTSM documentation.

“Used ChatGPT” is not an adequate declaration.

11. Study Mode and Socratic practice

Study Mode is useful for:

water balance;
Budyko;
infiltration;
hydrograph interpretation;
FDCs;
return period;
IDF curves;
rainfall-runoff relationships;
oral-assessment preparation.

For example:

I want to learn return period.

I do not want to memorise T = 1/p.
First diagnose my understanding.
Then give me an engineering-design situation.
Finally ask me about risk over the service life of the structure.

12. Three modes of use

Answer mode: “Calculate ET.”
Tutor mode: “Guide me to derive ET and check the units.”
Examiner mode: “Give me a problem, wait for my solution, then ask follow-up questions.”

For this course, prioritise tutor and examiner modes.

13. Free or Plus?

For IIO422, the Free plan is sufficient for most learning tasks.

Plus may become useful if you repeatedly need:

greater file capacity;
long debugging sessions;
higher tool availability;
longer or more complex analyses;
intensive use across several courses.

If your household budget is limited: start with Free and only pay for Plus after identifying a specific limitation that is genuinely affecting your work.

14. Five prompts worth saving

Concept

I want to learn [TOPIC].
First diagnose what I understand.
Then correct my gaps using an example from Chile.
Finish with a transfer question.

Problem solving

I will show you a problem and my attempt.
Do not solve it immediately.
Identify the first error, give me one hint, and wait.

Audit

Review the concept, equations, units, calculation,
interpretation, uncertainty and assumptions.

Oral practice

Give me a short oral assessment.
Ask one question at a time.
Use follow-up questions and correct me only at the end.

Error detection

Do not assume my method is correct.
Look for conceptual, numerical, methodological
and interpretative errors.

15. Final rule

Generative AI is permitted for learning activities and preparation of the practical assignments, but not during assessments. The syllabus also makes clear that being unable to explain a procedure included in a submission is evidence that the corresponding learning outcome has not been achieved.

The practical rule is therefore:

If you cannot explain, reproduce, modify and verify something that ChatGPT produced, you should not submit it as part of your work.

Sources

IIO422-Hydrology course syllabus, Universidad de La Frontera, 2026.
Baron, M. (2026). . The Koala News.
Tobor, J., & Sommer, T. (2026). . Hochschulforum Digitalisierung.
Vieriu, A. M., & Petrea, G. (2025). The impact of artificial intelligence (AI) on students’ academic development. Education Sciences, 15(3), 343.
Woon, A. (2025). . Higher Education Policy Institute.

Currency note: ChatGPT features, limits and prices change. Always check the official documentation.

How to Use ChatGPT to Learn Hydrological Modelling (I): set-up, prompts and trustworthy answers

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading time: 16-21 minutes

Before we begin: learning in an age of rapidly changing AI

Preparing university students for professional practice has become more difficult for one additional reason: we do not know exactly what AI tools will be capable of by the time today’s students graduate. Generative AI is evolving quickly and is already changing how we search for information, write, analyse data, program and solve problems. The educational challenge, therefore, is not merely to adopt a new technology, but to decide what to use it for and which student capabilities we actually want to strengthen.

Recent discussion highlights both opportunities and risks. Generative AI can widen access to explanations, personalise support and accelerate some tasks, but it can also encourage shallow learning, dependence and a false sense of mastery when it is used to produce polished answers without the necessary reasoning. In higher education, this has led to growing emphasis on critical thinking, adaptability, curiosity and lifelong learning, as well as on pedagogical frameworks that focus on purposeful integration rather than technology alone.

That is the purpose of this three-part tutorial series. It is not designed to teach you how to obtain quick answers. It is designed to help you use generative AI to build knowledge, question explanations, detect errors, practise reasoning, work more efficiently and receive feedback without outsourcing understanding. In IIO409, ChatGPT can help you write a function in R, propose a calibration strategy or explain GLUE in seconds. But you still need to be the person who can interpret a new result, modify a procedure and defend every modelling decision.

The sequence is deliberate. Part I focuses on setting up ChatGPT and obtaining useful, verifiable answers. Part II uses it as a Socratic tutor for conceptual understanding and critical thinking. Part III uses it as a base R programming companion for practical work and vibe coding without sacrificing reproducibility, validation or understanding.

ChatGPT can be genuinely useful for learning hydrological modelling, but its usefulness depends largely on how you use it. If you type only “Explain hydrological model calibration”, you may receive a correct general answer, but one that is still far too broad to be genuinely helpful in IIO409. If, instead, you define who you are, what you are learning, what your problem is, what prior knowledge you already have and what kind of answer you need, the conversation becomes much closer to a useful tutorial.

In IIO409 this matters especially. The course is not simply about running a rainfall-runoff model. You are expected to learn how to formulate a conceptual model, choose data and models, analyse sensitivity, calibrate and verify, interpret uncertainty, regionalise and discuss climate-change impacts. In other words, you must learn to make and defend modelling decisions.

1. Before you ask: set up the context

One of the simplest and most effective ways to improve ChatGPT’s replies is to give it stable information about yourself and about the course.

You do not need to write a biography. You need to provide the context that materially changes the answer.

A good initial context for an IIO409 student might be:

I am a Civil Engineering student in Chile taking IIO409 Hydrological Modelling.

I have already completed an R course and I can work with data.frame objects,
matrices, functions, plots and packages.
In this course I need to learn rainfall-runoff modelling, hydrometeorological data,
sensitivity analysis, calibration, verification, uncertainty, regionalisation
and climate change.

I work in base R. I do not want to use tidyverse.

When you help me:
- prioritise conceptual understanding and hydrological reasoning;
- do not invent references, R functions or results;
- separate facts, assumptions and inferences;
- if important information is missing, ask me before answering;
- for R code, deliver simple, reproducible and verifiable solutions;
- explain why each important step works;
- tell me how to check whether the result is correct.

You can store part of this information in Custom Instructions. Custom Instructions are available on both free and paid ChatGPT accounts, although the exact features and limits may vary by plan.

A particularly useful instruction is:

Before answering a technical task, check whether any missing information could materially change the answer.
If so, ask me up to three focused questions before continuing.

This simple rule reduces one of the most common failure modes: ChatGPT silently filling in missing information that you never provided.

Why does this help?

A language model does not automatically know your learning objective, your software ecosystem or the constraints of the task. When context is missing, it generates a plausible continuation. In hydrological modelling, a plausible assumption can still be methodologically wrong.

For example, if you ask:

How should I calibrate my model?

at least these questions are missing:

Which model?
Which variable are you calibrating against?
What is the purpose of the model?
What warm-up period are you using?
What are the calibration and verification periods?
What objective function do you want to optimise?
Which parameters are calibratable?
What ranges are physically acceptable?

A confident reply to such an underspecified question should make you cautious rather than reassured.

2. The R-C-T-F structure: Role + Context + Task + Format

There is no single magic formula for writing prompts. For this course, however, it is useful to think in four parts.

R: Role

State the perspective from which you want the answer.

Examples:

Act as a university tutor with expertise in hydrological modelling.

Act as a very critical methodological reviewer.

Act as a Socratic tutor. Do not give me the answer immediately.

The role does not magically turn ChatGPT into a true expert. It helps to guide the style and depth of the answer.

C: Context

Provide the information needed to understand the problem.

For example:

I am working on a pluvial catchment in south-central Chile.
I have daily precipitation, daily temperature and observed daily discharge.
I want to assess a conceptual rainfall-runoff model.

If you are working on the course project, add:

catchment;
period;
temporal resolution;
available data;
model;
aim of the analysis;
decisions already taken;
constraints.

T: Task

State exactly what ChatGPT must do.

A weak task:

Tell me about KGE.

A better one:

Explain which error components KGE attempts to summarise and why two simulations
with the same KGE can still behave very differently hydrologically.

Even better:

After explaining it, give me two hypothetical simulations with the same KGE but
different hydrological errors and ask me which one would be preferable for low flows.
Do not answer that last question until I reply.

F: Format

Tell ChatGPT how you want the answer delivered.

Answer in this order:
1. conceptual explanation;
2. hydrological example;
3. common mistake;
4. one question to check whether I understood.
Maximum 500 words.

For programming:

Provide:
1. strategy;
2. a base R function;
3. a small reproducible example;
4. checks of the result;
5. possible errors.
Do not use tidyverse.

3. A long prompt is not necessarily a good prompt

A common mistake is to assume that a prompt must be huge.

What matters is not length itself, but the removal of relevant ambiguity.

A good conversation can also be iterative:

Me: I need to learn global sensitivity analysis for IIO409.
Before explaining it, ask me what I already know.

ChatGPT: What do you understand by the sensitivity of a parameter?

Me: I think it measures how much the output changes when the parameter changes.

ChatGPT: Good. What limitation does that definition have if you vary one parameter while all others stay fixed?

This kind of exchange often produces more learning than asking for an encyclopaedic explanation of Sobol indices.

OpenAI’s Study Mode was designed around a similar logic: interactive questions, scaffolded explanations and checks of understanding. The underlying principle is simple and powerful: if you want to learn, do not ask only for content; ask to be questioned.

4. The instruction you should use for ambiguous problems

A very useful general rule is to tell ChatGPT explicitly that it should ask questions before solving when key information is missing.

For IIO409, I recommend making this a standard instruction:

Do not assume data, methods or objectives that I have not given you.
If missing information could change the solution, ask me before answering.
Ask at most three questions, prioritising the ones with the greatest methodological impact.

For instance:

My simulation obtained KGE = 0.76. Is my model good?

A methodologically serious response should ask, among other things:

good for what purpose?
is this calibration or verification?
which KGE components produce that value?
how does the model behave for the processes or flow ranges that matter?

Hydrological modelling is not about classifying isolated metrics as “good” or “bad”.

5. ChatGPT can still be wrong even when it sounds confident

A fluent reply is not evidence of correctness.

ChatGPT may:

invent a reference;
attribute an equation to the wrong author;
use a non-existent R function;
confuse function arguments;
assume units;
invent numerical values;
misread a figure;
suggest a methodological strategy that is not appropriate for your aim.

That is why you need a verification stage.

Rule 1: separate facts from proposals

Ask:

Separate your answer into:
- facts that can be checked;
- assumptions you are making;
- interpretation;
- recommendation.

Rule 2: request sources when they really matter

For each important scientific claim, provide a verifiable reference.
Do not invent DOI numbers. If you are not sufficiently sure of a reference, say so.

Then check the article yourself.

Do not cite ChatGPT as a substitute for a scientific source.

Rule 3: when dealing with R, run the code

Do not ask only:

Is this code correct?

Run it.

Check:

stopifnot(length(sim) == length(obs))
stopifnot(all(is.finite(sim)))
stopifnot(!anyNA(sim))

Inspect plots. Test the function on a small case with a known behaviour. Check dates and units.

Rule 4: ask for counter-examples

Give me a case in which this recommendation would be wrong.

This is particularly useful in modelling.

Rule 5: ask it to criticise itself

Now act as a critical reviewer.
Identify the three weakest points in your previous answer.

This does not guarantee correctness, but it often reveals hidden assumptions.

6. Do not ask it to think for you: ask it to help you think

If your aim is learning, avoid prompts like:

Solve this exercise.

Prefer:

I want to solve this exercise myself.
Do not give me the final solution.
Ask me one question at a time and only give a hint if I get stuck.

Another useful variation is:

First ask me to explain, in my own words, what I think will happen.
Then challenge my explanation.
Only at the end show me a reference solution.

This completely changes ChatGPT’s function: from answer generator to reasoning trainer.

7. Free or Plus for IIO409?

This question matters, especially when a monthly subscription would be a significant cost for the student’s household.

My recommendation for this course

I do not think students need ChatGPT Plus in order to pass IIO409 or to learn hydrological modelling well.

The free tier is often enough for:

studying concepts;
asking practice questions;
checking short fragments of R;
preparing discussion points;
using Study Mode;
rehearsing oral explanations.

A paid plan can be useful when you work intensively with longer conversations, files, code and repeated tool use. But this is mainly a matter of convenience and productivity, not educational necessity.

When might a paid plan be worth it?

It may make sense if:

you use ChatGPT heavily for programming and debugging;
you regularly work with uploaded files;
you analyse longer documents;
the free-tier limits interrupt your work often;
you are in a particularly intensive phase of the project.

When would I not pay for it?

I would not pay only to:

ask for definitions;
summarise notes;
generate practice questions;
review short code;
brainstorm study ideas.

For those tasks, the quality of the study method usually matters much more than the type of plan.

An equity consideration

No essential learning activity in the course should depend on a student’s ability to pay for a subscription. If two students have the same knowledge and one cannot afford a paid plan, that should not create an academic disadvantage.

Treat a paid plan, therefore, as an optional productivity tool, not as a requirement.

8. Five prompts you can save today

Prompt 1: Socratic tutor

Act as a Socratic tutor for hydrological modelling for a Civil Engineering student.
I want to learn [TOPIC].

First ask me what I currently understand.
Then ask me one question at a time.
Do not give me the solution before I answer.
When I make a mistake, identify the conceptual error and give me a hint.
At the end, give me a slightly different problem to test transfer.

Prompt 2: conceptual checker

I am going to explain [CONCEPT] in my own words.
Do not rewrite it immediately.

Assess my explanation in terms of:
1. correct ideas;
2. incomplete ideas;
3. mistakes;
4. implicit assumptions;
5. one question that reveals whether I really understand it.

Prompt 3: methodological critic

Act as a critical reviewer of a hydrological modelling study.
Do not try to be nice: look for methodological weaknesses.

I will describe my methodology.
Identify problems that could affect:
- data consistency;
- warm-up;
- calibration;
- verification;
- objective function;
- identifiability;
- uncertainty;
- interpretation.

Prioritise the problems by impact and explain how to check each one.

Prompt 4: programming companion

Help me solve this problem in base R, without tidyverse.

Before writing code:
1. summarise the goal;
2. identify inputs and outputs;
3. ask me for any crucial missing information.

Then deliver a minimal reproducible solution.
Include automatic checks and explain how to verify the result.
Do not invent functions or package arguments.

Prompt 5: hallucination detector

Review your previous answer as if you were an auditor.
Flag every claim that depends on:
- a reference;
- a software function;
- a number;
- a date;
- an assumption that I did not provide.

For each one, tell me how I can verify it independently.

9. Checklist before you trust an answer

Before using a reply from ChatGPT in IIO409, ask yourself:

Do I understand why the answer makes sense?
Have I identified its assumptions?
Can I explain it without copying its wording?
Can I think of at least one case in which it would not hold?
Have I checked the references and functions?
Have I run the code?
Have I checked units and dates?
Could I defend this decision in front of my lecturer?

If the answer to several of these is “no”, you are not finished yet.

10. Final idea: using ChatGPT well means asking better questions

The aim is not to memorise a set of “magic prompts”.

The aim is to develop a habit:

define the problem more clearly, make assumptions explicit, ask for evidence, test the result and refine the solution.

That is exactly the same habit you need in good hydrological modelling.

In Part II we will apply this logic to the theory component of IIO409: how to use ChatGPT to study concepts, read articles critically, diagnose modelling cases and prepare for assessments in which memorising definitions is not enough.

How to Use ChatGPT to Learn Hydrological Modelling (II): conceptual understanding and critical thinking

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading time: 18-22 minutes

In Part I we looked at setting up ChatGPT, giving it context, writing clearer prompts and checking its answers. Now the goal changes.

Here ChatGPT is not an encyclopaedia. It becomes a tutor, examiner, critical interlocutor and case generator.

The theory component in IIO409 is designed precisely to reduce the value of memorising definitions and to increase the value of understanding, interpreting, diagnosing and arguing:

\[ Theory = 0.40\,ECT + 0.20\,LCA + 0.25\,DMC + 0.15\,PC \]

where ECT stands for Conceptual Theory Assessments, LCA for Critical Reading of Scientific Articles, DMC for Modelling Diagnosis through Case Studies, and PC for Scientific Participation in Class.

The implication is important: if you use ChatGPT only to obtain ready-made answers, you are using it in the least useful way for this assessment design.

1. Your goal is not to remember: it is to build a mental model

Suppose you are studying equifinality.

You can ask:

What is equifinality?

You will get a definition.

But a definition is not the same thing as understanding.

Try this sequence instead:

Explain equifinality with an example from a conceptual rainfall-runoff model.

Then:

Now give me two parameter sets that could produce similar hydrographs
but different internal states. I do not need real numbers; I want to understand the mechanism.

Then:

Why might this problem remain hidden if I look only at NSE or KGE?

Then:

Now give me one plausible but incorrect statement about equifinality.
Do not tell me why it is wrong until I try to criticise it.

Finally:

Change the problem: now the aim is not total discharge reproduction, but low-flow analysis.
Does the importance of equifinality change? Ask me first what I think.

This turns a static definition into a structure of reasoning.

2. The Socratic ladder

OpenAI’s Study Mode is based on interactive questioning, scaffolded explanations and checks of understanding. Even without any special mode, you can reproduce that logic in your own prompting.

Use five levels.

Level 1: explain

Explain the concept with an example from a Chilean catchment.

Level 2: retrieve

Stop the explanation and ask me five questions, one at a time.
Do not show the answer until I reply.

Level 3: challenge

Look for weaknesses in my replies.
Do not correct only the outcome: identify the conceptual error.

Level 4: transfer

Change one important condition of the problem and ask whether my reasoning still holds.

Level 5: defend

Act as a lecturer in an oral defence.
Question my assumptions and ask for a justification of each decision.

If you can answer successfully at level 5, your understanding is probably much stronger than if you can merely repeat a definition.

3. ECT (40%): Conceptual Theory Assessments

ECT tasks will prioritise interpretation and reasoning.

To prepare well, you should not simply ask ChatGPT for “exam questions”. Instead, ask it for the type of cognitive work the assessment values.

3.1 Interpreting results

Prompt:

Generate a short hydrological modelling case with:
- performance in calibration and verification;
- bias;
- one efficiency metric;
- one visible feature of the hydrograph.

Ask me three interpretation questions.
Do not give the solutions until I answer.

Then ask:

Evaluate my reply by separating:
- observation;
- inference;
- conclusion that is not yet justified.

This distinction is extremely useful. Many student errors occur when an observation is turned immediately into a causal claim.

For example:

“The model underestimates peaks.”

is an observation.

“Precipitation must be underestimated.”

is a hypothesis, not a necessary conclusion.

3.2 Comparing methodological alternatives

Try:

Compare two calibration strategies:
A) optimise NSE;
B) optimise a metric that gives greater weight to low flows.

Do not tell me which one is better.
Set up a use case and ask me which I would choose and why.
Then change the use case.

The important idea here is that a methodological decision depends on the purpose of the model.

3.3 Working with scenarios

I have a model calibrated in a wet period.
Create a dry-period verification scenario.
Ask me what problems I would expect and what diagnostics I would perform.

Then:

Give me an alternative explanation to mine.

Learning to produce alternative explanations is essential if you want to avoid overconfident conclusions.

3.4 Finding assumptions

Ask:

Give me an apparently correct methodology for calibrating a conceptual model,
but hide five implicit assumptions.
Do not flag them.
My task will be to identify them.

Then compare your list with ChatGPT’s and discuss any differences.

4. How to study each main content block in IIO409

4.1 Hydrological models and conceptual models

Do not memorise only classifications.

You should be able to answer:

Which process is each store trying to represent?
Which processes are absent?
Which observations could discriminate between two structures?
Which parts of the discharge behaviour depend on which model components?

Prompt:

Describe a catchment with climate, seasonality, snow/no snow, vegetation,
geology and discharge regime.

Do not choose a model for me.
Ask me what processes I would include in my conceptual model and why.
Then critique my representation.

A more demanding exercise:

Propose two different conceptual models that could reproduce the same discharge behaviour.
Ask me what extra data I would use to discriminate between them.

4.2 Hydrometeorological data

The question is not only “What data exist?”, but:

Are these data suitable for the modelling question?

Try:

Give me a hypothetical data set for a Chilean catchment with five quality problems:
missing dates, inconsistent units, bias, station change or temporal-resolution problems.

Do not tell me the problems. Give me clues and ask me to diagnose them.

Or:

Compare an in situ source, a satellite product and a reanalysis for precipitation.
Build the comparison in terms of:
- resolution;
- representativeness;
- biases;
- coverage;
- implications for calibration.

Then give me one case where the apparently most precise option is not the best.

4.3 Sensitivity: from “which parameter matters” to “why”

For Sobol analysis you should understand at least the conceptual difference between first-order effects and interactions.

Prompt:

Generate hypothetical Sobol results for four parameters.
Include first-order and total indices.

Do not interpret the table.
Ask me:
1. which parameter dominates;
2. which one shows interaction;
3. what this implies for calibration;
4. what I cannot conclude from these indices.

A deeper question:

Can a weakly sensitive parameter still be physically important?
Make me argue both for and against.

This helps you separate sensitivity from “physical importance”, which are not the same thing.

4.4 Calibration and verification

Study calibration as a problem of inference and decision, not merely “finding the best parameter values”.

Prompt:

Give me a case in which a calibration with PSO obtains an excellent objective value,
but the model is still not adequate.

Include enough clues for me to diagnose the problem.
Do not give me the solution yet.

You should be able to discuss:

objective function;
warm-up period;
dependence on the calibration period;
parameter bounds;
overfitting;
stability across periods;
multiple optima;
equifinality;
the relation between purpose and metric.

Make ChatGPT challenge you:

I am going to defend this claim:
"The parameter set with the best KGE is the true parameter set of the catchment".

Argue with me as a lecturer.
Do not accept claims without justification.

4.5 Uncertainty and GLUE

An uncertainty band does not speak for itself.

Prompt:

Create a conceptual GLUE example with:
- 10,000 simulations;
- an acceptance threshold;
- a percentage of behavioural simulations;
- a predictive band.

Ask me to interpret what each element means.
Then ask me which sources of uncertainty are NOT necessarily represented.

Another important question:

If I increase or reduce the GLUE threshold, what effects should I expect?
Do not answer: make me predict first.

4.6 Regionalisation

Prompt:

I have an ungauged catchment and three potential donor catchments.
Create climatic, topographic and hydrological-signature information for the four.

My task will be to choose a regionalisation strategy.
Then question my similarity criterion.

You need to understand that geographical proximity and hydrological similarity are not synonyms.

4.7 Climate change

Here the key is to think in terms of a modelling chain.

Prompt:

Build a conceptual chain from climate scenarios to future discharge:
climate model -> downscaling/bias correction -> meteorological variables -> hydrological model -> indicators.

Hide three sources of uncertainty.
Ask me to identify them and explain how they propagate.

Then:

Now change just one methodological decision in the chain.
Ask me how the conclusions might change.

5. LCA (20%): Critical Reading of Scientific Articles

ChatGPT can summarise papers. That is probably one of the least demanding ways to use it.

For LCA you need to go further.

Step 1: read first yourself

Before asking ChatGPT anything, identify:

the problem;
the question;
the hypothesis;
the data;
the method;
the results;
the main conclusion.

Then use ChatGPT to compare with your interpretation.

I am going to give you a paper.
Do not summarise it first.

Ask me these questions one at a time:
1. What is the scientific question?
2. What is the hypothesis?
3. What evidence could falsify it?
4. Which methodological decisions are critical?
5. Which limitations affect the conclusion?

Step 2: separate result from interpretation

Build a table with:
- observed result;
- authors' interpretation;
- another plausible interpretation;
- evidence needed to distinguish between them.

Step 3: search for assumptions

Identify five methodological assumptions in the paper.
For each one, indicate which conclusion might change if the assumption fails.

Step 4: formulate a new question

Based only on the paper, propose five possible follow-up research questions.
Order them from a small extension to a genuinely new conceptual question.

Then decide yourself which one is scientifically meaningful.

Step 5: prepare an oral presentation

Do not ask:

Make my slides.

Instead:

Help me identify the three essential scientific messages.
Ask me first what I think is most important before proposing them.

The presentation should be a consequence of your understanding, not a substitute for it.

6. DMC (25%): Modelling Diagnosis through Case Studies

This component is especially suitable for studying with ChatGPT because it can generate endless variations of a case.

Base prompt:

Act as an IIO409 lecturer.

Create a realistic rainfall-runoff modelling case with at least four methodological problems.
The problems may involve data, warm-up, calibration, verification,
objective function, sensitivity, parameters, uncertainty or interpretation.

Do not mark the errors.
Give me only the case and then ask:
1. which problems I detect;
2. which one is most serious;
3. what consequences it would have;
4. how I would correct it.

After you answer:

Do not give me your full solution yet.
Tell me only which important problem I failed to detect.

Finally:

Now provide your full diagnosis and compare it with mine.

Make the cases progressively harder

Beginner level:

calibration and verification in the same period;
incorrect units;
no warm-up period.

Intermediate level:

objective function inconsistent with the modelling aim;
parameters at the bounds;
climate-change analysis with an inconsistent baseline.

Advanced level:

good aggregate metric but structured errors;
parameter compensation;
inconsistency between internal states and discharge;
parametric uncertainty presented as total uncertainty.

7. PC (15%): Scientific Participation in Class

Participation is not the same thing as talking often. It means making a contribution that improves the discussion.

ChatGPT can help before class.

Suppose the topic is parameter identifiability.

Tomorrow we will discuss parameter identifiability.

Give me:
- three conceptual questions that could open a discussion;
- two debatable statements;
- one example in which high sensitivity does not guarantee identifiability;
- one counter-argument to each statement.

Do not memorise the questions. Choose one that you actually understand and rephrase it in your own words.

You can also use ChatGPT to prepare hypotheses:

Give me five possible explanations for a parameter that changes strongly between two periods.
Classify them as:
- data;
- structure;
- optimisation;
- non-stationarity.

A scientifically useful classroom contribution might be:

“If the parameter changes between periods, how do we distinguish weak identifiability from structural compensation within the model?”

That connects concepts and opens discussion.

8. Feynman technique with ChatGPT

A good test of understanding is to explain a concept in your own words.

Prompt:

I am going to explain GLUE as if I were teaching it to a classmate who is just beginning.

Do not interrupt me.
When I finish:
1. identify what is correct;
2. find ambiguities;
3. detect important missing ideas;
4. ask me one question that my explanation cannot yet answer.

Then rewrite the explanation yourself.

Do not ask ChatGPT to rewrite it for you.

9. The “predict before you ask” method

This is one of the best study strategies for hydrological modelling.

Before consulting ChatGPT, write your own prediction:

If I increase a parameter associated with storage, I expect that...

Then ask:

Evaluate my prediction.
Do not focus only on whether the direction is correct.
Discuss under which conditions it could fail.

This prevents the passive habit of allowing ChatGPT to think first every time.

10. Build your own bank of mistakes

Each time you answer something incorrectly, record:

Concept:
My answer:
Error:
Why I got it wrong:
Correct principle:
New example:

After several weeks, ask:

Here is my error log.
Do not explain the topics again.
Identify patterns and create five new questions targeted specifically at my weaknesses.

This turns ChatGPT into an adaptive practice tool.

11. Master prompt for preparing an ECT

Act as a Civil Engineering lecturer in Hydrological Modelling.

Topic: [TOPIC].

I want to prepare for a conceptual assessment.
Do not test memorisation of definitions.

Generate five questions with increasing difficulty:
1. interpretation;
2. methodological comparison;
3. cause-effect;
4. diagnosis;
5. transfer to a new scenario.

Ask me one question at a time.
Wait for my answer.
Assess the reasoning, not only the conclusion.
When my answer is incomplete, use a hint before giving the solution.
At the end, identify my two main conceptual weaknesses.

12. Master prompt for DMC

Create a realistic hydrological diagnosis case for IIO409.

Include information about:
- data;
- model;
- warm-up;
- calibration;
- verification;
- objective function;
- parameters;
- results;
- uncertainty.

Introduce between three and five methodological problems of different severity.

Do not label them.
Ask me to:
1. identify them;
2. prioritise them;
3. explain the consequences;
4. propose corrections;
5. defend one alternative.

Then question my diagnosis as in an oral defence.

13. What not to do when studying theory with ChatGPT

Avoid turning your studying into:

Summary -> passive reading
Flashcards -> repetition without context
Automatic answers -> false confidence
AI-generated essay -> no practice of reasoning
Unquestioned explanations -> learning mistakes

The key question is always:

Can I apply this idea in a new case without ChatGPT telling me what to do?

If the answer is no, you are still studying too passively.

14. Before an assessment

Try this 45-minute routine:

10 min: retrieval

Without ChatGPT, write down everything you remember about the topic.

15 min: Socratic questioning

Use ChatGPT to identify gaps.

10 min: new case

Ask for a problem you have not seen before.

5 min: oral explanation

Explain it out loud without looking.

5 min: error log

Write down exactly what you did not understand.

This is far more useful for IIO409 than asking ChatGPT for “a short summary for the test”.

15. The goal: learn to think like a modeller

A good modeller is not defined by the ability to recall the longest definition.

A good modeller asks:

What does this model represent?
What does it not represent?
What evidence supports this decision?
What alternatives exist?
What assumption am I making?
How might I be wrong?
Which observation would distinguish between competing explanations?
Does the conclusion depend on the purpose?
What uncertainty remains?

ChatGPT can help you practise those questions again and again.

But only if you use it deliberately: make it question you, contradict you, change the conditions and demand that you justify your choices.

In Part III we will take the same logic into the practical side of the course: base R, vibe coding, reproducibility, debugging, sensitivity, calibration, uncertainty and preparation for the practical challenges.

How to use ChatGPT to learn Hydrology - Part II: theory, reasoning and assessment preparation

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading and practice time: 20-25 minutes.

In IIO422, theoretical assessment prioritises conceptual understanding and reasoning over memorisation or mechanical calculation. Questions may include conceptual problems, numerical exercises, interpretation of graphs and tables, analysis of hydrological situations, error diagnosis, comparison of methods, dimensional analysis, physical interpretation and integrative problems based on real catchments.

Your study strategy should reproduce those demands.

1. Recommended learning cycle

For each topic, use:

diagnosis
→ focused explanation
→ practice
→ correction
→ transfer
→ oral explanation

For example:

I want to study evapotranspiration.

First ask me five diagnostic questions.
Do not explain the topic until I answer.

Then identify my two main conceptual gaps,
correct them and give me two new problems.

Finish with a 90-second oral question.

2. Explicit map of the theoretical content

2.1. Introduction and basic concepts

You should understand:

definition and scope of Hydrology;
the hydrological cycle;
the general water-balance equation;
the concept of a catchment;
integrated water resources management;
spatial and temporal variability of hydrological processes.

Definition and scope

Make me explain what Hydrology studies and how it differs
from Meteorology, Hydraulics and Hydrogeology.

Do not accept a one-sentence definition.
Ask for:
1. object of study;
2. scales;
3. processes;
4. engineering applications;
5. one Chilean example.

Hydrological cycle and water balance

Treat a catchment as a control volume.

Make me identify inputs, outputs and storage changes.
Then change the temporal scale from daily to annual
and ask which terms may become small and which need not.

In simplified form:

Inputs - Outputs = Change in storage

or, for a catchment:

P - Q - ET = Delta S

The objective is not to memorise the equation, but to understand what it includes and when the simplification is defensible.

Catchments and integrated water resources management

Compare a river catchment with an administrative boundary.

Ask why a catchment is useful for hydrological analysis
and why integrated water resources management must also consider
users, institutions, infrastructure and ecosystems.

Spatial and temporal variability

Use precipitation, soil moisture and streamflow.

Make me compare their expected spatial and temporal variability
in an Andean catchment and explain why they cannot all be observed
with the same network or resolution.

2.2. Water in the atmosphere

The syllabus includes:

basic climatology and atmospheric circulation;
solar radiation;
air temperature;
humidity and water vapour;
precipitation;
interception;
evaporation;
evapotranspiration;
spatial interpolation of hydrological variables;
the Budyko framework.

Climatology and atmospheric circulation

Relate atmospheric circulation, topography and precipitation
across Chile.

Make me compare a northern catchment, a Mediterranean catchment
and a southern catchment before giving the explanation.

Radiation, temperature, humidity and water vapour

Build a causal chain:
radiation → temperature → vapour pressure → evaporative demand.

Make me distinguish direct relationships from those
that depend on other variables.

Precipitation

Give me an hourly storm.

Make me distinguish:
- intensity;
- accumulated depth;
- duration;
- temporal resolution;
- antecedent dry period.

Then change only the temporal resolution and ask what information is lost.

Interception

Compare two events with the same total rainfall:
one over a forested catchment and one over sparse vegetation.

Make me reason when interception can be hydrologically important
and when its relative effect becomes smaller.

Evaporation and evapotranspiration

Make me distinguish evaporation, transpiration,
potential ET and actual ET.

Then give one water-limited and one energy-limited situation.

Interpolation

Compare Thiessen polygons, inverse-distance weighting
and kriging for catchment rainfall estimation.

Do not ask which is 'best'.
Give me a station network and make me choose according to
network density, topography, objective, variability and data availability.

Budyko framework

Make me interpret a Budyko diagram.

Ask:
- what the axes represent;
- what water-limited and energy-limited mean;
- what information is required;
- why a deviation does not automatically imply an error.

2.3. Water in the soil

The syllabus includes:

flow through porous media;
infiltration;
Green-Ampt;
land use and soil types.

Flow through porous media

Make me explain why water can move through unsaturated soil
without reducing the explanation to 'gravity pulls it down'.

Require discussion of gradients and hydraulic properties.

Infiltration

Compare the same storm over an initially dry and an initially wet soil.

Ask me how infiltration, storage, runoff generation
and streamflow response are expected to change.

Green-Ampt

Do not give me the equation first.

Help me reconstruct Green-Ampt from its assumptions:
a distinct wetting front, changes in water content
and capillary forces.

Then show the equation and make me perform dimensional analysis.

Land use and soil types

Compare forest, agricultural land and an urbanised area.

Make me separate the effects of:
- texture;
- structure;
- compaction;
- vegetation cover;
- impervious surfaces.

Do not let me attribute everything to 'soil type'.

2.4. Surface runoff

You should understand:

hydrological information;
streamflow measurement;
hydrographs;
flow-duration curves (FDCs);
effective rainfall and direct runoff;
rainfall-runoff relationships.

Streamflow measurement

Make me distinguish stage measurement, gauging
and streamflow estimation from a rating curve.

Then give me a flood beyond the gauged range
and ask what uncertainty is introduced.

Hydrographs

Show me a hydrograph and make me identify:
baseflow, rising limb, peak, lag, recession and direct-runoff volume.

Do not accept purely geometric descriptions:
require interpretation of processes.

FDCs

Make me interpret Q10, Q50 and Q90.
Include a trap involving exceedance and non-exceedance probability.

Effective rainfall and direct runoff

Give me a storm and hydrograph.
Make me distinguish total rainfall, abstractions,
effective rainfall and direct runoff.

2.5. Simplified hydrological models for annual water balance

The syllabus includes simplified hydrological modelling for catchment-scale annual water balance.

Give me a catchment with P, E and Q time series.

Make me decide what can be estimated directly,
what requires modelling, and which storage components
remain poorly observed.

Do not treat the model as a black box. Ask which assumptions about scale and mass balance are embedded in the model.

2.6. Probabilistic and statistical methods

Conceptually, you should understand:

exploratory data analysis and descriptive statistics;
probabilistic treatment of hydrological information;
frequency and probability functions;
return period;
statistical parameters;
fitting probability distributions;
probability distributions of hydrological variables.

Make me explain F(x), 1-F(x), exceedance probability,
quantiles and return period using annual maxima.

Do not use equations until the interpretation is clear.

2.7. Rainfall intensities and design

The syllabus includes:

maximum 24-hour precipitation;
maximum 1-, 2- and 3-day precipitation;
Intensity-Duration-Frequency (IDF) curves;
design hyetographs.

Give me an IDF table.

Make me:
1. select duration and T;
2. convert intensity to depth;
3. explain why intensity and duration are not interchangeable;
4. construct a conceptual design hyetograph;
5. identify one extrapolation limitation.

2.8. Unit hydrographs, design floods and HEC-HMS

The syllabus includes:

unit and synthetic hydrographs;
design-flood calculation using SCS-CN;
introduction to HEC-HMS.

Make me explain the linearity and superposition assumptions
of the unit hydrograph.

Then give me a situation where those assumptions are weak.

For SCS-CN:

Do not give me only the calculation.
Make me interpret how antecedent condition, land use
and CN affect effective rainfall and runoff.

For HEC-HMS:

Explain what each main component of an event-based HEC-HMS model represents
and what information I should check before accepting a simulation.

3. How theory is assessed

Theory = 0.15 × Tests
 + 0.30 × Test 1
 + 0.40 × Test 2
 + 0.15 × Individual Oral Assessment

Individual Tests - 15%

Purpose: progressive understanding and continuous study.

Generate a five-question micro-test:
- two conceptual;
- one on units;
- one interpretation;
- one error-diagnosis question.

Ask one at a time.

Test 1 - 30%

Focuses mainly on:

hydrological processes;
catchment characterisation;
annual water balance.

Create a Chilean catchment problem combining
P, ET, Q, storage and physical catchment characteristics.

Assess formulation, units, calculation, interpretation and uncertainty.

Test 2 - 40%

Integrates:

frequency analysis;
extreme events;
design rainfall and streamflow;
rainfall-runoff relationships;
hydrological modelling.

Create an integrative problem.

It must force me to combine at least three parts of the course
and justify an engineering decision.

Individual Oral Assessment - 15%

There are two brief individual oral assessments, one after each major test.

Simulate a 6-minute individual oral assessment.

Ask one question at a time.
Require me to:
- explain concepts in my own words;
- relate processes;
- interpret a result;
- justify a decision;
- identify a limitation;
- answer follow-up questions.

Correct me only at the end.

4. Practise the same task types used by the course

Conceptual questions

Make me explain why a 100-year return period
does not mean 'once every 100 years'.

Numerical problems

Assess separately:
formulation, equations, units, calculation and interpretation.

Graph and table interpretation

Practise with:

time series;
climographs;
hydrographs and hyetographs;
FDCs;
hydroclimatic maps;
hypsometric curves;
Budyko diagrams;
empirical and theoretical distributions;
frequency curves;
IDF curves;
hydrological-model results.

Error diagnosis

Construct a solution containing exactly three plausible errors:
one conceptual, one dimensional and one methodological.
Do not identify them.

Method comparison

Make me choose only after defining:
objective, data, scale, assumptions, uncertainty and limitations.

Dimensional analysis

Generate expressions involving P, Q, area, volume,
time and intensity.
Make me demonstrate which are dimensionally consistent.

Physical interpretation

After every calculation, ask:

Is the sign plausible?
Is the order of magnitude plausible?
Which process controls this result?
What additional observation would increase confidence?

5. Use ChatGPT to prepare peer discussion

Give me a conceptual multiple-choice question with five options
and exactly one correct answer.

Do not identify the answer.
I will answer first.
Then give me two plausible arguments that another student
might use to defend a different option.
Finally make me answer again.

6. The perturbation technique

Once a problem is solved, change only one condition:

Now double the antecedent soil moisture.
Do not recalculate immediately.
First ask what I expect to change and why.

or:

Keep annual P fixed but change its seasonal distribution.
Which conclusions from the annual water balance still hold?

This reproduces the course sequence: application → perturbation → interpretation → defence.

7. A 25-minute study routine

0-5 min: retrieval without notes.
5-12 min: diagnosis and correction.
12-20 min: new problems and perturbations.
20-25 min: oral explanation and follow-up questions.

Key ideas

Study in the same way you will be assessed.
Connect processes rather than memorising chapters.
Include Budyko, IDF, design hyetographs, SCS-CN and HEC-HMS in your conceptual map.
Practise with real data and figures from Chilean catchments.
Require dimensional consistency, interpretation and uncertainty.
Train explicitly in error diagnosis.
Practise oral explanations throughout the semester.
AI may support learning, but it is not permitted during assessments.

Sources

IIO422-Hydrology course syllabus, Universidad de La Frontera, 2026.

How to Use ChatGPT to Learn Hydrological Modelling (III): base R, vibe coding and reproducible projects

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading time: 20-25 minutes

In this third part we will use ChatGPT as a programming companion for solving hydrological-modelling problems in base R, without tidyverse.

We assume that you have already taken an R course and know the fundamentals: objects, vectors, matrices, data.frame objects, functions, conditionals, loops, basic plotting and the use of packages.

The goal here is not to teach R from the beginning. It is to learn a new workflow:

describe -> generate -> run -> check -> interpret -> modify -> document

This is often called vibe coding: conversational programming with AI support. It can speed up work considerably, but it can also produce convincing-looking code that is conceptually wrong.

In IIO409 the rule should be:

AI may write code. You still remain responsible for knowing what problem the code solves, why it solves it in that way, and how to check whether the result is correct.

1. What the practical component really assesses

The practical component is:

\[ Practical = 0.25\,PRE + 0.10\,DTM + 0.35\,DPI + 0.10\,PFG + 0.20\,DTI \]

where:

PRE = Reproducible Team Project;
DTM = Technical Modelling Dossier;
DPI = Individual Practical Challenges;
PFG = Final Group Presentation;
DTI = Individual Technical Defence.

In addition, to pass the practical component you must achieve at least 4.0 in the combined average of the individual components DPI and DTI.

This completely changes how it makes sense to use ChatGPT.

If ChatGPT writes a perfect script but you cannot modify it during an individual challenge or explain a modelling decision in the defence, then the code did not help you learn.

2. Responsible vibe coding

A good workflow has seven steps.

Step 1: specify the problem

Do not begin with:

Write me code to calibrate a model.

First define:

inputs;
outputs;
units;
temporal resolution;
model;
objective;
constraints;
success criterion.

Example:

I have daily precipitation [mm/day], mean temperature [°C] and discharge [m3/s]
for a catchment of 850 km2.

I want a base R function that:
1. aligns the series by date;
2. detects missing values;
3. converts discharge to mm/day;
4. returns a data.frame ready for modelling.

Do not use tidyverse.
Before programming, tell me what additional information you need.

Step 2: ask for a minimal solution

Do not ask for 300 lines of code.

Implement the minimum working version first.
Use base R functions.
Do not add optimisation or plotting yet.

Small solutions are easier to verify.

Step 3: run it immediately

Never read a long script and assume it works.

Copy the minimum version, run it and inspect:

str(x)
head(x)
summary(x)

Check sizes:

dim(x)
length(x)

Check missing values:

colSums(is.na(x))

Step 4: inspect the meaning, not only the object

A vector can have the right length and still be conceptually wrong.

Ask:

Are dates aligned?
Are the units correct?
Is the time ordering correct?
Are there duplicates?
Are the values physically plausible?
Have missing values been handled explicitly?

Step 5: test

Ask:

Now create three simple tests that will fail if:
- dates are unsorted;
- discharge is negative;
- the lengths do not match.

For example:

stopifnot(!is.unsorted(dat$date))
stopifnot(all(dat$q >= 0 | is.na(dat$q)))
stopifnot(nrow(dat) == length(dat$date))

Step 6: explain

Explain each decision in the code that could affect the hydrological result.
Do not describe trivial syntax.

This distinction matters.

read.csv() is syntax.

Converting m3/s to a daily depth over the catchment is a quantitative decision that you must understand.

Step 7: refactor

Only afterwards:

Turn the solution into reusable functions.
Add argument validation.
Keep base R and minimal dependencies.

3. Core R skills you still need

ChatGPT can help with syntax, but you must still recognise and understand the following structures.

3.1 Paths and project structure

Avoid:

setwd("C:/Users/my_name/Desktop/Project")

Prefer a project directory and relative paths.

file.path("data", "precipitation.csv")

Ask ChatGPT:

Review this project and identify absolute paths that harm reproducibility.
Suggest replacements using file.path().

3.2 Reading and writing data

You should be comfortable with:

dat <- read.csv("data/input.csv")
write.csv(dat, "results/output.csv", row.names = FALSE)

saveRDS(dat, "results/data_processed.rds")
dat2 <- readRDS("results/data_processed.rds")

Always ask:

What information might be lost if I save this object as CSV rather than RDS?

3.3 Dates

dat$date <- as.Date(dat$date)

For date-time values:

dat$datetime <- as.POSIXct(
 dat$datetime,
 tz = "UTC",
 format = "%Y-%m-%d %H:%M:%S"
)

Date errors can ruin a calibration without necessarily triggering a coding error.

Ask:

Give me tests that help verify whether two hydrological series really represent the same days.

3.4 Subsetting

idx <- dat$date >= as.Date("2000-01-01") &
 dat$date <= as.Date("2010-12-31")

cal <- dat[idx, ]

You should be able to define explicit periods for:

warm-up;
calibration;
verification.

3.5 Missing data

Do not replace NA automatically.

First inspect:

colSums(is.na(dat))

Then decide what to do.

Ask:

I have 2% missing precipitation values.
Do not recommend interpolation immediately.
Ask me about duration, temporal distribution and modelling purpose before suggesting a treatment.

3.6 Functions

The basic unit of a reproducible project should be a clear function.

run_experiment <- function(par, input) {
 stopifnot(is.numeric(par))
 stopifnot(is.data.frame(input))

 # run model
 sim <- ...

 sim
}

Ask ChatGPT to avoid monolithic scripts:

Split this script only when there is a clear functional responsibility.
Do not create unnecessary functions.

3.7 `apply`, `lapply` and loops

You should understand both styles.

out <- lapply(files, read.csv)

or:

out <- vector("list", length(files))

for (i in seq_along(files)) {
 out[[i]] <- read.csv(files[i])
}

There is no need to replace all loops with apply functions. The criterion is readability and correctness.

3.8 Base graphics

For diagnostics:

plot(obs, sim,
 xlab = "Observed",
 ylab = "Simulated")

abline(0, 1)

Time series:

plot(dat$date, dat$obs, type = "l")
lines(dat$date, dat$sim)

Residuals:

res <- dat$sim - dat$obs
plot(dat$date, res, type = "h")
abline(h = 0)

Ask ChatGPT:

Do not suggest a plot just because it looks nice.
Tell me what hydrological diagnostic question each plot helps answer.

3.9 Randomness control

For sensitivity, calibration or uncertainty analyses:

set.seed(1234)

The seed should be recorded whenever it matters.

3.10 Error handling

if (!all(required %in% names(dat))) {
 stop("Missing required columns.")
}

For operations that may fail:

ans <- tryCatch(
 run_model(par),
 error = function(e) NA
)

But do not hide errors indiscriminately.

Ask:

In what situations would tryCatch() hide a methodological problem that should actually stop the analysis?

3.11 Packages

Use explicit namespace calls when they improve clarity:

hydroGOF::KGE(sim, obs)

Before trusting a function suggested by AI, check the documentation:

help(package = "hydroGOF")
?hydroGOF::KGE

or consult the official package documentation.

ChatGPT can invent function names or arguments. The documentation is the authority.

3.12 Recording the environment

At the end of an analysis:

sessionInfo()

Save it.

Also record:

R version;
packages;
seed;
parameters;
periods;
input files;
execution date when relevant.

4. Structure of a reproducible project

A possible structure is:

IIO409_project/
|
|-- 00_data/
| |-- raw/
| `-- processed/
|
|-- 01_scripts/
| |-- 01_read_data.R
| |-- 02_qc.R
| |-- 03_model.R
| |-- 04_sensitivity.R
| |-- 05_calibration.R
| |-- 06_verification.R
| `-- 07_uncertainty.R
|
|-- 02_results/
|-- 03_figures/
|-- 04_docs/
|-- config.R
`-- README.md

ChatGPT can help you audit this structure:

Act as a reproducibility auditor.
I will paste the file tree and the main scripts.
Identify:
- absolute paths;
- manual steps;
- objects created outside scripts;
- parameters written in multiple places;
- undocumented dependencies;
- result files that cannot be rebuilt.

5. Centralised configuration

Avoid repeating key parameters across many scripts.

cfg <- list(
 warmup_start = as.Date("2000-01-01"),
 calibration_start = as.Date("2001-01-01"),
 calibration_end = as.Date("2010-12-31"),
 validation_start = as.Date("2011-01-01"),
 validation_end = as.Date("2020-12-31"),
 seed = 1234L
)

Then:

source("config.R")

This improves traceability.

6. Working with hydrometeorological data

A sensible workflow is:

read -> validate -> sort -> align -> convert units -> diagnose -> model

Prompt:

I have these columns:
date, p_mm, t_c, q_m3s.

Before modelling, create a quality-control checklist.
For each check:
- explain why it matters hydrologically;
- provide base R code;
- indicate which action should NOT be automated without inspection.

Examples of checks:

stopifnot(!anyDuplicated(dat$date))
stopifnot(!is.unsorted(dat$date))

summary(dat$p_mm)
summary(dat$t_c)
summary(dat$q_m3s)

Negative precipitation:

which(dat$p_mm < 0)

Negative discharge:

which(dat$q_m3s < 0)

Do not delete suspicious values automatically. Investigate them.

7. Converting discharge to a depth

This is a good exercise in both concept and programming.

Ask:

Do not give me the formula immediately.
Make me derive how to convert mean daily discharge [m3/s] into runoff depth [mm/day]
for a catchment with area A [km2].
Check the dimensional consistency of each step.

Then implement it yourself:

q_to_mm_day <- function(q_m3s, area_km2) {
 stopifnot(area_km2 > 0)

 volume_m3_day <- q_m3s * 86400
 area_m2 <- area_km2 * 1e6

 (volume_m3_day / area_m2) * 1000
}

Test it dimensionally and with simple cases.

8. Implementing the hydrological model

For TUWmodel, GR4J or any other model used in the course, avoid asking AI to re-implement everything from scratch if a trusted function or lecturer-provided code already exists.

A better use is:

Here is the documentation of the function we are going to use.
Do not invent arguments outside this documentation.

Explain:
1. inputs;
2. outputs;
3. the meaning of each parameter;
4. units;
5. relevant internal states;
6. three checks to perform before running it.

Then:

Write a base R wrapper to run the model and return:
- the simulation;
- metrics;
- parameters;
- the period.
Include argument validation.

Your wrapper should make the project’s modelling decisions explicit.

9. Sensitivity analysis

Do not begin by asking only:

Do Sobol.

First define:

parameters;
ranges;
output of interest;
sample size;
metric;
seed;
computational cost.

Prompt:

I want to perform a global Sobol sensitivity analysis.

Before writing code, build with me a decision table with:
parameter, range, justification, output, sample size, seed and expected cost.

Do not choose values arbitrarily without marking them as assumptions.

After you run it:

Here are my first-order and total indices.
Do not interpret them immediately.
Ask me four questions to check whether I understand interaction and dominance.

10. Calibration with PSO

AI can help you configure the experiment, but it should not silently decide:

bounds;
objective function;
period;
number of particles;
stopping rule.

Create an explicit objective function.

Skeleton:

objective_function <- function(par, input, obs) {
 sim <- run_model(par, input)

 if (length(sim) != length(obs)) {
 stop("sim and obs have different lengths")
 }

 score <- ...

 score
}

Prompt:

Review this objective function.
Do not change the code yet.

Look for:
- information leakage;
- NA values;
- length mismatches;
- max/min orientation;
- wrong period;
- warm-up dependence;
- units.

If you use hydroPSO, check the documentation of the version actually installed.

Do not trust an argument merely because ChatGPT suggested it confidently.

11. Calibration is not validation

One useful check is:

stopifnot(max(cal_dates) < min(val_dates))

This is only one example, but it captures the idea: encode important decisions as tests.

Ask:

Give me five programmatic tests that reduce the risk of accidentally using
validation data during calibration.

12. Metrics and diagnosis

Do not rely on a single metric.

You may calculate metrics with appropriate packages or verified functions and complement them with diagnostic plots.

Ask:

I have NSE, KGE and PBIAS for calibration and verification.
Do not classify the model yet.
Tell me what additional information I should inspect for three different aims:
1. water balance;
2. low flows;
3. flood peaks.

The same simulation can be useful for one aim and inadequate for another.

13. GLUE and uncertainty

A typical computational workflow involves:

generating parameter sets;
running the model;
calculating a performance measure;
applying a behavioural threshold;
analysing the distribution of results;
building diagnostics.

Ask ChatGPT to work in blocks:

Do not write the whole GLUE analysis in one script.

First design the functions we need and their interfaces.
Then we will implement and test them one by one.

Conceptual example:

evaluate_par <- function(par, input, obs) {
 sim <- run_model(par, input)
 score <- ...
 c(score = score)
}

Before running thousands of simulations, test five.

set.seed(1234)

Then ask:

Which problems might not appear with five simulations but could appear with 100,000?

This introduces issues such as memory, execution time, single-run failures and result storage.

14. Regionalisation

For regionalisation you will probably combine catchment attributes and hydrological signatures.

You should be able to handle basic matrix and data.frame operations.

Example:

attrs <- data.frame(
 basin = c("A", "B", "C"),
 p_mean = c(1200, 950, 1300),
 elev = c(850, 620, 910)
)

d <- dist(scale(attrs[, c("p_mean", "elev")]))
as.matrix(d)

Critical question:

What is the limitation of using scale() and Euclidean distance if attributes have
different distributions, relevance or collinearity?

Programming should lead into methodological discussion.

15. Climate change

Here reproducibility becomes essential because the modelling chain is long.

You can ask:

Design a file structure and a set of functions for a workflow:
climate data -> preprocessing -> bias correction/downscaling -> hydrological model
-> indicators -> period comparison.

Do not write the code yet.
First identify which metadata must be kept to reproduce each step.

Keep separate:

original data;
processed data;
scenarios;
outputs;
indicators.

Never overwrite the original inputs silently.

16. Debugging: provide the full error context

Do not write:

It does not work.

Provide:

1. the goal;
2. the minimal code;
3. the full error message;
4. the expected result;
5. the obtained result;
6. the structure of the objects involved.

Prompt:

This is a minimal reproducible example.
Do not rewrite everything.

1. identify the most likely cause;
2. explain which part of the error message supports it;
3. propose the smallest possible change;
4. give me a test that verifies the fix.

The “smallest possible change” prevents unnecessary rewrites of the whole project.

17. When the code runs but the result is wrong

This is the most dangerous situation.

Ask:

The code runs without errors, but the hydrograph looks suspicious.
Give me an ordered diagnostic strategy from the simplest checks
to structural problems in the model.
Do not assume the issue is calibration.

A sound diagnosis should consider:

data;
time alignment;
units;
warm-up;
PET;
parameters;
objective function;
implementation;
conceptual structure.

18. Ask for tests before you optimise

Prompt:

Here is my run_model() function.
Before optimising anything, create a small set of tests.

I want to check:
- arguments;
- dimensions;
- NA handling;
- reproducibility;
- behaviour with out-of-range parameters;
- unit consistency.

You do not need a huge testing framework to benefit from this.

19. PRE (25%): Reproducible Team Project

Use ChatGPT as an auditor, not as an invisible author.

Once a week:

Audit the reproducibility of our current project.

I will give you:
- the file tree;
- README;
- config;
- scripts.

Look for steps that only work because we know manually what to do.

Another helpful review:

Could a third person run this project from scratch?
List everything they would still have to guess.

That prompt usually reveals many weaknesses.

20. DTM (10%): Technical Modelling Dossier

The dossier should explain decisions.

A simple table helps:

Decision	Choice	Alternative	Justification	Consequence
Warm-up	…	…	…	…
Objective function	…	…	…	…
Parameter range	…	…	…	…
GLUE threshold	…	…	…	…

ChatGPT can challenge the table:

Act as a reviewer.
For each row in this table, formulate one question that would force the team
to justify the decision with evidence or hydrological reasoning.

Do not ask it to invent the justification for you.

21. DPI (35%): Individual Practical Challenges

This is the most important practical component.

Prepare by practising variations, not by repeating the same script.

Here is an exercise that I have already solved.
Create a variation that changes two important conditions.
Do not only change the numbers.

I want it to force me to modify the code and reinterpret the result.

Examples:

a different period;
missing data;
another objective function;
a parameter at its bound;
a change of temporal resolution;
a new catchment;
a different hydrological aim.

To practise properly:

Do not give me code for the first 15 minutes.
Only answer conceptual questions and review my plan.

22. PFG (10%): Final Group Presentation

ChatGPT can help you remove information, not only add it.

We have 12 results.
Our scientific message is [MESSAGE].

Help us select the four results that are strictly necessary.
For each result we exclude, explain why it is not essential.

Then:

Formulate five difficult questions that a lecturer might ask after the presentation.

23. DTI (20%): Individual Technical Defence

This is probably one of the best ways to use ChatGPT before assessment.

Act as an oral examiner for IIO409.

I will describe our project.
Ask me individual questions about:
- decisions;
- parameters;
- sensitivity;
- calibration;
- performance;
- uncertainty;
- limitations;
- alternative scenarios.

Ask one question at a time.
If my answer is superficial, go deeper.
Do not praise me or give hints too early.

Then:

Change one decision in the project and ask what consequences I would expect.

That is exactly the kind of reasoning you will need in the defence.

24. Git and version control

For a team project, Git is strongly recommended.

Minimum skills:

git status
git add
git commit
git pull
git push

ChatGPT can help interpret errors, but do not execute destructive commands that you do not understand.

Prompt:

Explain this Git conflict.
Do not give me a resolution command yet.
First explain what happened and what information I could lose with each alternative.

25. Minimum README

Your README.md should explain:

1. objective;
2. data;
3. structure;
4. requirements;
5. order of execution;
6. generated outputs;
7. configurable decisions;
8. authors/contact.

Prompt:

Audit this README from the perspective of a person who has never seen the project.
What information is still missing to reproduce it?

26. A template prompt for almost any R problem

Save this one:

Act as a scientific programmer with expertise in R and hydrological modelling.

CONTEXT
[describe data, model, units, period and objective]

TASK
[what you need to achieve]

CONSTRAINTS
- base R; no tidyverse.
- Minimal dependencies.
- Do not invent package functions or arguments.
- Reproducible code.
- Validate inputs.
- Use set.seed() if there is randomness.
- Do not hide important errors.

PROCESS
Before writing code:
1. summarise the problem;
2. identify crucial missing information;
3. propose a minimal strategy.

Then:
4. deliver the code;
5. create a small example;
6. add checks;
7. explain how to validate the result hydrologically;
8. identify possible failure modes.

27. The most important prompt for learning code written by AI

After you receive any script, ask:

Now remove the finished solution from your explanation.

Make me reconstruct this code block by block.
Ask me what each block should do before showing it.

If you cannot reconstruct it, you probably have not learned it.

28. Final rules for vibe coding in IIO409

Never run 10,000 simulations before testing 5.
Never calibrate before checking data, units and dates.
Never use a function suggested by AI without checking the documentation.
Never accept a metric without looking at the hydrological behaviour.
Never confuse code that runs with methodology that is sound.
Never submit a script that you cannot modify.
Never present a decision that you cannot defend.
Keep seeds, configuration, versions and metadata.
Separate raw data, processed data and results.
Use ChatGPT to test and question your work, not merely to produce it.

The professional skill we want is not simply the ability to write R faster.

It is the ability to build a modelling chain whose logic, code, data, results and limitations you can explain and reproduce.

If you use ChatGPT in this way, AI can speed up mechanical tasks while you concentrate effort on what really matters: thinking like a hydrological modeller.

How to use ChatGPT to learn Hydrology - Part III: vibe coding, hydroTSM and reproducible practical projects

Sun, 16 Aug 2026 00:00:00 +0000

Estimated reading and practice time: 20-25 minutes.

This tutorial starts from an explicit assumption: you already know how to program in R. The objective is therefore not to review vectors, data.frame objects, functions or loops, but to learn how to use AI to accelerate hydrological analysis while retaining technical control over data, methods, code, results and interpretation.

In IIO422, practical work must be reproducible and every student must be able to understand and modify the procedures used.

We will therefore use a controlled vibe-coding approach.

1. What vibe coding means in this course

It does not mean:

Do the practical assignment in R.

It means working iteratively:

hydrological question
→ specification
→ proposed code
→ execution and testing
→ audit
→ interpretation
→ modification

AI acts as a copilot. You decide what problem should be solved, whether the data are valid, which method is appropriate and whether the result is hydrologically plausible.

2. The practical component is one final project divided into TP-01 and TP-02

For assessment:

Practical = 0.45 × TP-01 + 0.55 × TP-02

Each TP combines:

35% Reproducible Hydrological Project - team
15% Technical Evidence Dossier - team
30% Hydrological Defence - individual
20% Supervised Practical Challenge - individual

The implication is direct: a script produced by ChatGPT may improve the team submission while simultaneously reducing your individual mark if you cannot explain it.

3. Map of practical competences

The practical work combines:

hydrometeorological time-series analysis;
catchment characterisation;
water balance;
Budyko;
probabilistic methods;
extreme events;
hydrological design;
hydrological simulation;
reproducibility;
interpretation for water management and infrastructure safety.

4. TP-01: hydrological processes and annual water balance

The syllabus specifies that TP-01 includes, among other elements:

physical and hydroclimatic catchment characterisation;
catchment delineation and geomorphological analysis;
collection and basic quality control of hydrometeorological information;
analysis of precipitation, temperature, evapotranspiration and streamflow;
water-balance estimation;
application of the Budyko framework;
analysis of water supply and demand;
simplified hydrological modelling;
interpretation from a water-resources management perspective.

Starting prompt for TP-01

Act as a hydrological reviewer for TP-01.

Do not write code yet.

Help me turn the overall objective into verifiable questions:
1. What are the physical characteristics of the catchment?
2. What is its hydroclimatic regime?
3. What data do I need?
4. How will I check data quality?
5. How will I close the water balance?
6. How will I use Budyko?
7. What can I conclude about water supply and demand?
8. What uncertainty must I report?

5. Use base R + hydroTSM for time series

hydroTSM is appropriate for manipulating, aggregating, analysing and visualising hydrological time series.

library(zoo)
library(hydroTSM)

Potentially useful functions include:

hydroTSM::daily2monthly()
hydroTSM::daily2annual()
hydroTSM::monthlyfunction()
hydroTSM::annualfunction()
hydroTSM::fdc()
hydroTSM::hydroplot()
hydroTSM::plot_pq()
hydroTSM::climograph()

Do not use a function simply because ChatGPT suggested it.

Verify that the function exists.

Explain:
- input;
- output;
- units;
- handling of NA;
- temporal assumptions;
- a reasonable base-R alternative.

6. Initial data audit

Before analysis:

I have daily P, T, ET and Q series.

Design an audit covering:
- temporal coverage;
- regularity;
- NA;
- duplicates;
- units;
- physically impossible values;
- changes in station or source;
- temporal consistency among variables.

The quality of the analysis depends on this stage.

7. Temporal aggregation: think before coding

P and Q do not necessarily use the same aggregation operator.

I have:
daily P in mm/day
daily mean Q in m3/s
catchment area in km2

Before writing code, make me derive how to obtain:
- monthly P;
- monthly mean Q;
- monthly volume;
- monthly equivalent runoff depth in mm.

You should be able to reconstruct the conversion dimensionally.

8. Budyko and annual water balance

TP-01 explicitly requires the Budyko framework.

I have annual P, ET/PET and Q.

Help me build a Budyko diagnostic.

Before coding:
1. check units;
2. define the dimensionless indices;
3. ask what each axis means;
4. identify potentially anomalous years;
5. separate physical interpretation from possible data error.

9. Simplified hydrological modelling and airGRteaching

The syllabus includes simplified models for annual water-balance analysis and lists airGRteaching as a course resource.

A useful introduction is to work with a daily model and then analyse the outputs at annual scale.

A typical workflow is:

PREP <- airGRteaching::PrepGR(
 ObsDF = BasinObs,
 HydroModel = "GR4J",
 CemaNeige = FALSE
)

CAL <- airGRteaching::CalGR(
 PrepGR = PREP,
 CalCrit = "KGE2",
 CalPer = c("1990-01-01", "1994-12-31")
)

SIM <- airGRteaching::SimGR(
 PrepGR = PREP,
 Param = CAL,
 EffCrit = "KGE2",
 SimPer = c("1995-01-01", "1999-12-31")
)

Do not memorise these calls. You should understand:

input data;
units;
warm-up period;
calibration;
simulation;
efficiency criterion;
parameters;
water balance;
the difference between statistical fit and hydrological realism.

Controlled vibe coding with airGRteaching

I am using GR4J with airGRteaching.

Work step by step:
1. review format and units;
2. check periods;
3. generate only PrepGR;
4. wait for me to execute it;
5. interpret the output;
6. only then generate CalGR;
7. make me explain the criterion;
8. continue with SimGR;
9. finish with a defence question.

10. TP-02: frequency analysis and hydrological extremes

The syllabus states that TP-02 includes:

exploratory analysis of maximum-value series;
selection and fitting of probability distributions;
parameter estimation;
goodness-of-fit analysis;
estimation of rainfall and streamflow for different return periods;
analysis of record-length effects;
uncertainty evaluation;
simulation of a flood event with HEC-HMS;
comparison of observed and simulated streamflow;
implications for design and infrastructure safety.

Use this list directly as your work plan.

11. Exploratory analysis and descriptive statistics

Before fitting a distribution:

Do not fit anything yet.

Design an EDA for annual maxima:
- coverage;
- outliers;
- visual trend;
- descriptive parameters;
- skewness;
- independence;
- sample size;
- recommended plots.

Do not use a fitted distribution to conceal a poorly reviewed series.

12. Probabilistic treatment

You should be able to explain:

sample;
random variable;
distribution function;
exceedance;
non-exceedance;
quantiles;
return period;
statistical parameters.

Make me explain F(x), 1-F(x), T and a quantile
without equations first.

Then translate the reasoning into R.

13. Fitting probability distributions

Do not ask:

Which distribution is best?

Ask:

I have annual maxima.

Make me define:
- candidate distributions;
- estimation method;
- support;
- graphical diagnostics;
- goodness of fit;
- tail behaviour;
- extrapolation uncertainty.

Then request code in small blocks.

14. Effect of record length

This is an explicit component of TP-02.

I have 40 years of annual maxima.

Design an experiment comparing estimates from 15, 25 and 40 years.

Before coding:
- define what remains fixed;
- define what metric will be compared;
- decide how uncertainty will be shown;
- identify what conclusions cannot be generalised.

15. Return period and risk

I want to estimate a T-year event.

Before using a q*() function:
make me derive the correct non-exceedance probability
for the quantile function I am using.

For risk:

Make me derive the probability of at least one exceedance
during n years of service life.

Do not give me the formula initially.

16. Intensities, IDF curves and design hyetographs

I have an IDF table.

Help me construct a design hyetograph.

Before coding:
1. define T;
2. define duration;
3. define time step;
4. choose a temporal pattern;
5. check conservation of total rainfall depth;
6. explain which assumption controls the temporal distribution.

17. SCS-CN

Let us implement SCS-CN.

First define:
- P;
- CN;
- potential maximum retention;
- initial abstraction;
- effective rainfall.

Then generate a simple R function.
Include unit checks and limiting cases.

If the code runs but you cannot explain what changes when CN changes, you do not yet understand the method.

18. HEC-HMS flood simulation

TP-02 explicitly includes a flood simulation using HEC-HMS.

ChatGPT can help you:

review model structure;
interpret parameters;
document scenarios;
diagnose results;
compare observed and simulated streamflow.

But it should not invent parameter values.

I am configuring HEC-HMS.

Do not propose parameter values yet.

Make me review:
- catchment;
- loss method;
- transform method;
- baseflow;
- routing, where relevant;
- design storm;
- time step;
- initial conditions;
- simulation period.

19. Compare observed and simulated flow critically

Do not reduce evaluation to a single metric.

I have Qobs and Qsim.

Design an evaluation including:
- hydrograph;
- peak;
- peak timing;
- volume;
- bias;
- one global performance metric;
- an error that matters for infrastructure safety.

20. Error diagnosis: a core competence

The course deliberately incorporates incorrect results, plots, code or methods.

Practise like this:

Generate an R block for frequency analysis
with exactly two plausible errors.

Do not identify them.

I must:
1. detect them;
2. explain the hydrological consequence;
3. correct them;
4. compare the result.

21. Reproducibility

A suggested structure is:

TP/
├── README.md
├── data/
│ ├── raw/
│ └── processed/
├── R/
│ ├── 01_qc.R
│ ├── 02_tp01_hydroclimate.R
│ ├── 03_budyko_balance.R
│ ├── 04_frequency.R
│ ├── 05_design_event.R
│ └── 06_outputs.R
├── models/
├── output/
│ ├── figures/
│ └── tables/
└── evidence/

The team should provide data, metadata, scripts, parameters, configuration files and everything else required to regenerate the results.

22. Use ChatGPT as a reproducibility auditor

Act as a reproducibility auditor.

Look for:
- absolute paths;
- undeclared dependencies;
- manually created objects;
- scripts run out of order;
- hidden parameters;
- inconsistent units;
- non-reproducible outputs;
- non-existent functions;
- undocumented steps.

23. Technical Evidence Dossier

The dossier replaces the traditional long written report.

A useful evidence chain is:

question
→ method
→ result
→ evidence
→ interpretation
→ uncertainty
→ limitation

Do not fill space with generic definitions.

24. Prepare for the Hydrological Defence

I will give you the complete project.

Ask random questions about:
- catchment delineation;
- data;
- QC;
- water balance;
- Budyko;
- hydroTSM;
- frequency analysis;
- distributions;
- T;
- uncertainty;
- IDF;
- SCS-CN;
- HEC-HMS;
- modelling;
- results;
- limitations.

Ask one question at a time.

Every team member should understand the complete project.

25. Prepare for the Supervised Practical Challenge

The individual challenge lasts approximately 30-45 minutes and has three parts:

conceptual diagnosis;
technical solution;
hydrological interpretation.

Generate a 35-minute individual challenge.

Use a small dataset.
Include:
A. conceptual diagnosis;
B. an R task;
C. hydrological interpretation.

Insert one plausible error.
Do not use tidyverse.

26. The modification rule

After any AI-generated code:

Now make me modify it for:
- another period;
- another unit;
- another treatment of NA;
- another T;
- another distribution;
- another hydrological assumption.

If you cannot modify it, you are not ready to defend it.

27. Declare AI use

Each TP should identify:

tool;
purpose;
component;
verification.

For example:

Tool: ChatGPT.
Purpose: debugging a function that converts Q to mm.
Component: 03_budyko_balance.R.
Verification: independent dimensional derivation,
known-value test case and comparison with a manual calculation.

28. Master prompt for the practical project

Act as a tutor in R programming and Hydrology.

I already know R.
Do not use tidyverse.
Prefer base R and hydroTSM.
Where relevant, consider airGRteaching and HEC-HMS.

Do not be the author of the project.

Rules:
1. start with the hydrological question;
2. separate data, method and assumptions;
3. provide code in small blocks;
4. do not invent data or functions;
5. require units;
6. include checks;
7. make me execute before continuing;
8. require interpretation;
9. make me modify the code;
10. finish with a defence question.

29. Final competence

By the end of the course, you should be able to:

audit hydrometeorological series;
characterise a catchment;
analyse P, T, ET and Q;
quantify a water balance;
interpret Budyko;
analyse water supply and demand;
use a simplified hydrological model;
construct and interpret an FDC;
perform frequency analysis;
fit and compare probability distributions;
estimate design events;
evaluate uncertainty and record-length effects;
construct design storms;
apply SCS-CN;
configure and review a simulation in HEC-HMS;
compare observed and simulated streamflow;
reproduce the full workflow;
defend the decisions made.

If ChatGPT helps you develop these capacities, vibe coding is functioning as assisted learning.

If it merely produces a script that “runs”, it is hiding what you still do not know.

Sources and documentation

IIO422-Hydrology course syllabus, Universidad de La Frontera, 2026.

Academic integrity: AI is permitted as support for learning and practical-project preparation, but not during assessments. Any AI-generated content remains the student’s responsibility and must be verifiable, reproducible and defensible.

ChatGPT | Dr. Mauricio Zambrano-Bigiarini

How to use ChatGPT to learn Hydrology - Part I: configuration, context and useful prompts

Why this series of tutorials?

1. The fundamental rule: tutor, not autopilot

2. Configure the context that actually matters

3. Connect ChatGPT with the Learning Outcomes

4. The anatomy of a good prompt

Role

Context

Task

Constraints

Output

5. Make the model recognise missing information

6. Use the course learning sequence as a dialogue structure

7. Separate facts, assumptions, results and uncertainty

8. Fluency does not imply truth

9. AI is not a scientific authority

10. Declare AI use in practical assignments

11. Study Mode and Socratic practice

12. Three modes of use

13. Free or Plus?

14. Five prompts worth saving

Concept

Problem solving

Audit

Oral practice

Error detection

15. Final rule

Sources

How to Use ChatGPT to Learn Hydrological Modelling (I): set-up, prompts and trustworthy answers

Before we begin: learning in an age of rapidly changing AI

1. Before you ask: set up the context

Why does this help?

2. The R-C-T-F structure: Role + Context + Task + Format

R: Role

C: Context

T: Task

F: Format

3. A long prompt is not necessarily a good prompt

4. The instruction you should use for ambiguous problems

5. ChatGPT can still be wrong even when it sounds confident

Rule 1: separate facts from proposals

Rule 2: request sources when they really matter

Rule 3: when dealing with R, run the code

Rule 4: ask for counter-examples

Rule 5: ask it to criticise itself

6. Do not ask it to think for you: ask it to help you think

7. Free or Plus for IIO409?

My recommendation for this course

When might a paid plan be worth it?

When would I not pay for it?

An equity consideration

8. Five prompts you can save today

Prompt 1: Socratic tutor

Prompt 2: conceptual checker

Prompt 3: methodological critic

Prompt 4: programming companion

Prompt 5: hallucination detector

9. Checklist before you trust an answer

10. Final idea: using ChatGPT well means asking better questions

Recommended references and further reading

How to Use ChatGPT to Learn Hydrological Modelling (II): conceptual understanding and critical thinking

1. Your goal is not to remember: it is to build a mental model

2. The Socratic ladder

Level 1: explain

Level 2: retrieve

Level 3: challenge

Level 4: transfer

Level 5: defend

3. ECT (40%): Conceptual Theory Assessments

3.1 Interpreting results

3.2 Comparing methodological alternatives

3.3 Working with scenarios

3.4 Finding assumptions

4. How to study each main content block in IIO409

4.1 Hydrological models and conceptual models

4.2 Hydrometeorological data

4.3 Sensitivity: from “which parameter matters” to “why”

4.4 Calibration and verification

4.5 Uncertainty and GLUE