Meny
 

Refining the Committee Approach and Uncertainty Prediction in Hydrological Modelling

Due to the complexity of hydrological systems a single model may be unable to capture the full range of a catchment response and accurately predict the streamflows. A solution could be the in use of several specialized models organized in the so-called committees. Les mer
Vår pris
2279,-

(Innbundet) Fri frakt!
Leveringstid: Sendes innen 21 dager
På grunn av Brexit-tilpasninger og tiltak for å begrense covid-19 kan det dessverre oppstå forsinket levering.

Innbundet
Legg i
Innbundet
Legg i
Vår pris: 2279,-

(Innbundet) Fri frakt!
Leveringstid: Sendes innen 21 dager
På grunn av Brexit-tilpasninger og tiltak for å begrense covid-19 kan det dessverre oppstå forsinket levering.

Om boka

Due to the complexity of hydrological systems a single model may be unable to capture the full range of a catchment response and accurately predict the streamflows. A solution could be the in use of several specialized models organized in the so-called committees. Refining the committee approach is one of the important topics of this study, and it is demonstrated that it allows for increased predictive capability of models.


Another topic addressed is the prediction of hydrologic models' uncertainty. The traditionally used Monte Carlo method is based on the past data and cannot be directly used for estimation of model uncertainty for the future model runs during its operation. In this thesis the so-called MLUE (Machine Learning for Uncertainty Estimation) approach is further explored and extended; in it the machine learning techniques (e.g. neural networks) are used to encapsulate the results of Monte Carlo experiments in a predictive model that is able to estimate uncertainty for the future states of the modelled system.


Furthermore, it is demonstrated that a committee of several predictive uncertainty models allows for an increase in prediction accuracy. Catchments in Nepal, UK and USA are used as case studies.


In flood modelling hydrological models are typically used in combination with hydraulic models forming a cascade, often supported by geospatial processing. For uncertainty analysis of flood inundation modelling of the Nzoia catchment (Kenya) SWAT hydrological and SOBEK hydrodynamic models are integrated, and the parametric uncertainty of the hydrological model is allowed to propagate through the model cascade using Monte Carlo simulations, leading to the generation of the probabilistic flood maps. Due to the high computational complexity of these experiments, the high performance (cluster) computing framework is designed and used.


This study refined a number of hydroinformatics techniques, thus enhancing uncertainty-based hydrological and integrated modelling.

Fakta

Innholdsfortegnelse

SUMMARY


1 INTRODUCTION
1.1 Background
1.1.1 Conceptual hydrological models
1.1.2 Committee hydrological models (multi-models)
1.1.3 Uncertainty analysis of hydrological models
1.1.4 Uncertainty analysis using machine learning techniques
1.1.5 Committee of predictive uncertainty models
1.1.6 Flood inundation models and their uncertainty
1.2 Research questions
1.3 Research objectives
1.4 Case studies
1.4.1 Alzette catchment
1.4.2 Bagmati catchment
1.4.3 Brue catchment
1.4.4 Leaf catchment
1.4.5 Nzoia catchment
1.5 Terminology
1.6 Outline of the thesis


2 CONCEPTUAL AND DATA-DRIVEN HYDROLOGICAL MODELLING
2.1 Introduction
2.2 HBV hydrological models for the considered case studies
2.2.1 HBV model brief characterization
2.2.2 Software development of HBV model
2.2.3 Models setup
2.2.3.1. HBV model setup for the Brue catchment
2.2.3.2. HBV model setup for the Bagmati catchment
2.2.3.3. HBV model setup for the Nzoia catchment
2.2.3.4. HBV model setup for the Leaf catchment
2.2.3.5. HBV model setup for the Alzette catchment
2.3 SWAT model for the Nzoia catchment
2.3.1 SWAT model description
2.3.2 Inputs for the SWAT model
2.4 Calibration of hydrological models
2.4.1 Single objective optimization
2.4.2 Multi objective optimization
2.4.3 SWAT-NSGAX tool and its application
2.5 Data driven modelling
2.5.1 Introduction
2.5.2 Machine learning in data-driven rainfall-runoff modelling
2.5.3 Artificial neural networks
2.5.4 Model trees
2.5.5 Locally weighted regression
2.5.6 Selection of input variables
2.5.7 Data-driven rainfall-runoff model of the Bagmati catchment
2.5.8 Data-driven rainfall-runoff model of the Leaf catchment
2.6 Summary


3 COMMITTEES OF HYDROLOGICAL MODELS
3.1 Introduction
3.2 Specialized hydrological models
3.3 Committees of specialized models
3.3.1 Fuzzy committee models
3.3.2 States-based committee models
3.3.3 Inputs-based committee models
3.3.4 Outputs-based committee models
3.4 P

Om forfatteren