VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Environmental systems analysis
Last Updated: 2026-02-05 15:13:05
Abstract
Gain overview of and practice in model-based data analysis.
Objective
- Learn to construct, calibrate, and test models for the description of data gained from environmental systems. - Learn to assess the identifiability of estimated model parameters and to improve experimental/measurement design to improve identifiability. - Learn to identify model deficiencies, to improve the model structure to better fulfil the statistical assumptions, and to find an adequate model complexity. - Learn to estimate model prediction uncertainty.
Content
- Fields of model application (causes of uncertainty in model predictions, mathematical representation of models, construction of models). - Model identification (frequentist and Bayesian inference, sensitivity analysis, identifiability analysis, model structure selection and model averaging). - Model testing (frequentist and Bayesian testing). - Prediction uncertainty (intrinsic indefiniteness of system behaviour, uncertainty in model parameters, model structure, external influence factors, numerical solution). - Outlook (use of models in decision support).
Resources
Lecture Notes
Extensive manuscript available.
Literature
Literature overview is given in the manuscript.
General Information
- Language
- English
- Levels
- MSC
- Frequency
- Yearly recurring
Examination
- Type
- session examination
- Mode
- oral 30 minutes
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture with exercise | Environmental systems analysis |
|
2 h weekly |