Course on Predictive Models for Flood Risk
Online course of 300 hours in predictive models for flood risk, structured in 6 modules covering flood risk data, extreme value statistics, hydrological forecasting, machine learning, and risk and decision-making under the Floods Directive 2007/60/EC, Royal Decree 903/2010 and ISO 31000, with an assigned technical tutor.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Identify the data sources needed to model flood risk.
Apply extreme value statistics to hydrological time series.
Understand operational hydrological forecasting systems.
Develop machine learning models for streamflow.
Translate forecasts into risk and expected damage.
Communicate uncertainty to decision-makers.
Build a predictive flood risk model.
Who it's for
- Flood risk analysts.
- Hydrological data scientists.
- Hydrologists moving into data-driven forecasting.
- Early warning system technicians.
- Catastrophe modellers in insurance.
- Civil protection officers.
- Engineering or science graduates aiming to work in river basin authorities.
What you'll work with
- Directive 2007/60/EC (assessment and management of flood risks)
- Royal Decree 903/2010 (Spanish regulation on flood risk assessment and management)
- Law 17/2015 (Spanish National Civil Protection System)
- Basic Civil Protection Planning Directive for Flood Risk (Spanish framework for flood emergency planning)
- Royal Legislative Decree 1/2001 (consolidated text of the Spanish Water Act)
- Royal Decree 849/1986 (Regulation on the Public Water Domain)
- ISO 31000 (risk management)
- Python with scikit-learn and TensorFlow
- R with extRemes
- HEC-HMS
- QGIS
- Google Earth Engine
6 modules
1.1Types of flooding: fluvial, pluvial and coastal1.2Hazard, exposure and vulnerability1.3Hydrometeorological data sources1.4Automatic Hydrological Information System (SAIH)1.5Weather radar and satellite1.6Digital terrain models1.7Damage and insurance claims data1.8Quality control and homogenisation of time series1.9National Flood Zone Mapping System1.10Case study: event database for a river basin
2.1Flood frequency analysis2.2GEV, Gumbel and log-Pearson III distributions2.3Annual maximum and peaks-over-threshold methods2.4Fitting by maximum likelihood and L-moments2.5Confidence intervals2.6Non-stationarity and climate change2.7Regional frequency analysis2.8Copulas for compound events2.9Bootstrap resampling of uncertainty2.10Practical exercise: GEV fitting of maximum flows in R
3.1Conceptual rainfall-runoff models3.2Data assimilation3.3Ensemble forecasting3.4Numerical weather prediction3.5Radar nowcasting3.6European Flood Awareness System (EFAS)3.7Forecast verification3.8Warning thresholds3.9Communicating uncertainty3.10Workshop: forecast verification with skill scores
4.1Preparation of hydrological data4.2Regression and random forests4.3LSTM neural networks for streamflow4.4Classification of flood-susceptible areas4.5Surrogate models of hydraulic models4.6Temporal cross-validation4.7Explainability with SHAP4.8Comparison with physically based models4.9Operational deployment of the model4.10Lab: streamflow prediction with LSTM
5.1Depth-damage curves5.2Expected annual damage5.3Risk maps5.4Insurance and the Spanish Insurance Compensation Consortium5.5Early warning systems5.6Civil protection plans5.7Cost-benefit analysis of measures5.8Decision-making under uncertainty5.9Risk communication5.10Case study: expected annual damage of a municipality
6.1Selection of the river basin and the problem6.2Data collection and cleaning6.3Exploratory analysis of the time series6.4Development of the statistical model6.5Development of the machine learning model6.6Validation and comparison6.7Translation into risk and warnings6.8Operational recommendations for management6.9Report and presentation6.10Final project: final review with the tutor
How you'll learn
The course is 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within the intake, so it fits around your job.
Each module combines theory, guided reading of the original regulations and standards and applied exercises. The working software is Python with scikit-learn and TensorFlow, R with extRemes, HEC-HMS, QGIS and Google Earth Engine, in free, academic or evaluation versions. Practical work is based on real procedures: fitting of extreme value distributions, development of streamflow prediction models and calculation of expected annual damage. Assessment is continuous per module plus the final project.
Standards covered: Directive 2007/60/EC; Royal Decree 903/2010; Law 17/2015; Basic Civil Protection Planning Directive for Flood Risk; Royal Legislative Decree 1/2001; Royal Decree 849/1986; ISO 31000.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- No prior qualification is required.
- An internet connection and a computer able to run the programme's software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 300 hours over 3 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Python with scikit-learn and TensorFlow, R with extRemes, HEC-HMS, QGIS and Google Earth Engine, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute certificate, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
No prior qualification is required; you need an internet connection, a computer able to run the programme's software and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Smart Water Grids in Cities Course
Online course of 300 hours in smart water grids in cities, structured in 6 modules covering smart water networks, remote meter reading and smart meters, pressure…
Course on Urban Climate Resilience Plans
Online course of 300 hours in urban climate resilience plans, structured in 6 modules covering urban climate risk, risk and vulnerability assessment, adaptation measures, plan preparation…
Road Safety Audits in Cities Course
Online course of 300 hours in road safety audits in cities. 6 modules covering the audit framework, methodology and checklists, design-stage audits, inspection of roads in…
More in Civil, Rail & Smart Cities
All Civil, Rail & Smart Cities programmes → · How to apply · Fees & financing · Scholarships