Skip to main content

Research Repository

Advanced Search

Sensitivity analysis for comparison, validation and physical-legitimacy of neural network-based hydrological models

Dawson, C.W.; Mount, Nick J.; Abrahart, R.J.; Louis, J.

Sensitivity analysis for comparison, validation and physical-legitimacy of neural network-based hydrological models Thumbnail


Authors

C.W. Dawson

NICK MOUNT nick.mount@nottingham.ac.uk
Chief Executive Uon Online

R.J. Abrahart

J. Louis



Abstract

This paper addresses the difficult question of how to perform meaningful comparisons between neural network-based hydrological models and alternative modelling approaches. Standard, goodness-of-fit metric approaches are limited since they only assess numerical performance and not physical legitimacy of the means by which output is achieved. Consequently, the potential for general application or catchment transfer of such models is seldom understood. This paper presents a partial derivative, relative sensitivity analysis method as a consistent means by which the physical legitimacy of models can be evaluated. It is used to compare the behaviour and physical rationality of a generalised linear model and two neural network models for predicting median flood magnitude in rural catchments. The different models perform similarly in terms of goodness-of-fit statistics, but behave quite distinctly when the relative sensitivities of their inputs are evaluated. The neural solutions are seen to offer an encouraging degree of physical legitimacy in their behaviour, over that of a generalised linear modelling counterpart, particularly when overfitting is constrained. This indicates that neural models offer preferable solutions for transfer into ungauged catchments. Thus, the importance of understanding both model performance and physical legitimacy when comparing neural models with alternative modelling approaches is demonstrated.

Journal Article Type Article
Publication Date Jan 1, 2014
Deposit Date Jan 30, 2015
Publicly Available Date Jan 30, 2015
Journal Journal of Hydroinformatics
Print ISSN 1464-7141
Electronic ISSN 1464-7141
Publisher IWA Publishing
Peer Reviewed Peer Reviewed
Volume 16
Issue 2
DOI https://doi.org/10.2166/hydro.2013.222
Keywords generalised linear model; index flood; neural network; partial derivative; physical legitimacy; sensitivity analysis; ungauged catchment
Public URL https://nottingham-repository.worktribe.com/output/998249
Publisher URL http://www.iwaponline.com/jh/016/jh0160407.htm
Additional Information ©IWA Publishing 2014. The definitive peer-reviewed and edited version of this article is published in Journal of Hydroinformatics,16(2), 407–424 doi: 10.2166/hydro.2013.222 and is available at www.iwapublishing.com

Files





You might also like



Downloadable Citations