Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

Kayastha, N. (IHE Delft Institute for Water Education)
Solomatine, D.P. (TU Delft Water Resources; IHE Delft Institute for Water Education)
Lal Shrestha, D. (CSIRO Land and Water)

Piasecki, M (editor)

2014

In the MLUE method (reported in Shrestha et al. [1, 2]) we run a hydrological model M for multiple realizations of parameters vectors (Monte Carlo simulations), and use this data to build a machine learning model V to predict uncertainty (quantiles) of the model M output. In this paper, for model V, we employ three machine learning techniques, namely, artificial neural networks, model tree, locally weighted regression which leads to several models results. We propose to use the simple averaging method (SA) and the weighted model averaging method (WMA) to form a committee of these models. These approaches are applied to estimate uncertainty of streamflows simulation in Bagmati catchment in Nepal. Tests on the different data sets show that WMA performs a bit better than SA.

uncertainty analysis
hydrological model
machine learning
MLUE
model averaging

http://resolver.tudelft.nl/uuid:f019e42b-f46e-4371-a492-3fed87e04ce2

978-1-5108-0039-7

Proceedings of the HIC 2014 - 11th international conference on hydroinformatics

11th International Conference on Hydroinformatics, 2014-08-17 → 2014-08-21, New York, United States

Institutional Repository

conference paper

© 2014 N. Kayastha, D.P. Solomatine, D. Lal Shrestha