Improved validation framework and R-package for artificial neural network models

Humphrey, Greer B. and Maier, Holger R. and Wu, Wenyan and Mount, Nick J. and Dandy, Graeme C. and Abrahart, R.J. and Dawson, C.W. (2017) Improved validation framework and R-package for artificial neural network models. Environmental Modelling and Software, 92 . pp. 82-106. ISSN 1364-8152

[img] PDF - Repository staff only until 28 February 2018. - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Available under Licence Creative Commons Attribution Non-commercial No Derivatives.
Download (3MB)

Abstract

Validation is a critical component of any modelling process. In artificial neural network (ANN) modelling, validation generally consists of the assessment of model predictive performance on an independent validation set (predictive validity). However, this ignores other aspects of model validation considered to be good practice in other areas of environmental modelling, such as residual analysis (replicative validity) and checking the plausibility of the model in relation to a priori system understanding (structural validity). In order to address this shortcoming, a validation framework for ANNs is introduced in this paper that covers all of the above aspects of validation. In addition, the validann R-package is introduced that enables these validation methods to be implemented in a user-friendly and consistent fashion. The benefits of the framework and R-package are demonstrated for two environmental modelling case studies, highlighting the importance of considering replicative and structural validity in addition to predictive validity.

Item Type: Article
Keywords: Artificial neural networks; Multi-layer perceptron; R-package; Structural validation; Replicative validation; Predictive validation
Schools/Departments: University of Nottingham, UK > Faculty of Social Sciences > School of Geography
Identification Number: 10.1016/j.envsoft.2017.01.023
Depositing User: Mount, Dr Nick
Date Deposited: 02 Mar 2017 11:49
Last Modified: 13 Oct 2017 01:40
URI: http://eprints.nottingham.ac.uk/id/eprint/40959

Actions (Archive Staff Only)

Edit View Edit View