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

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

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...

Full description

Bibliographic Details
Main Authors: Dawson, C.W., Mount, Nick J., Abrahart, R.J., Louis, J.
Format: Article
Published: IWA Publishing 2014
Subjects:
generalised linear model; index flood; neural network; partial derivative; physical legitimacy; sensitivity analysis; ungauged catchment
Online Access:https://eprints.nottingham.ac.uk/28054/

Similar Items

Similar Items