HS2.3.3

Bayesian approaches have become increasingly popular in water quality modelling, thanks to their ability to handle uncertainty comprehensively (data, model structure and parameter uncertainty) and as flexible statistical and data mining tools. Furthermore, graphical Bayesian Belief Networks can be powerful decision support tools that make it relatively easy for stakeholders to engage in the model building process. The aim of this session is to review the state-of-the-art in this field and compare software and procedural choices in order to consolidate and set new directions for the emerging community of Bayesian water quality modellers.

In particular, we seek contributions from water quality research that use Bayesian approaches to, for example but not exclusively:
• quantify the uncertainty of model predictions
• quantify especially model structural error through, for example, Bayesian Model Averaging or structural error terms
• address the problem of scaling (e.g. disparity of scales between processes, observations, model resolution and predictions) through hierarchical models
• model water quality in data sparse environments
• compare models with different levels of complexity and process representation
• use statistical emulators to allow probabilistic predictions of complex modelled systems
• integrate prior knowledge, especially problematizing the choice of Bayesian priors
• produce user-friendly decision support tools using graphical Bayesian Belief Networks
• involve stakeholders in model development and maximise the use of expert knowledge
• use machine-learning and data mining approaches to learn from large, possibly high-resolution data sets.

Share:
Co-organized by BG4
Convener: Miriam GlendellECSECS | Co-conveners: Ibrahim Alameddine, Lorenz AmmannECSECS, Hoseung JungECSECS, James E. Sample
Displays
| Attendance Mon, 04 May, 10:45–12:30 (CEST)

Bayesian approaches have become increasingly popular in water quality modelling, thanks to their ability to handle uncertainty comprehensively (data, model structure and parameter uncertainty) and as flexible statistical and data mining tools. Furthermore, graphical Bayesian Belief Networks can be powerful decision support tools that make it relatively easy for stakeholders to engage in the model building process. The aim of this session is to review the state-of-the-art in this field and compare software and procedural choices in order to consolidate and set new directions for the emerging community of Bayesian water quality modellers.

In particular, we seek contributions from water quality research that use Bayesian approaches to, for example but not exclusively:
• quantify the uncertainty of model predictions
• quantify especially model structural error through, for example, Bayesian Model Averaging or structural error terms
• address the problem of scaling (e.g. disparity of scales between processes, observations, model resolution and predictions) through hierarchical models
• model water quality in data sparse environments
• compare models with different levels of complexity and process representation
• use statistical emulators to allow probabilistic predictions of complex modelled systems
• integrate prior knowledge, especially problematizing the choice of Bayesian priors
• produce user-friendly decision support tools using graphical Bayesian Belief Networks
• involve stakeholders in model development and maximise the use of expert knowledge
• use machine-learning and data mining approaches to learn from large, possibly high-resolution data sets.

Session assets

Session materials Download all presentations (25MB)