Skip to main content

Research Repository

See what's under the surface

Advanced Search

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

Humphrey, Greer B.; Maier, Holger R.; Wu, Wenyan; Mount, Nick J.; Dandy, Graeme C.; Abrahart, R.J.; Dawson, C.W.

Authors

Greer B. Humphrey

Holger R. Maier holger.maier@adelaide.edu.au

Wenyan Wu

Nick J. Mount nick.mount@nottingham.ac.uk

Graeme C. Dandy

R.J. Abrahart bob.abrahart@nottingham.ac.uk

C.W. Dawson c.w.dawson1@lboro.ac.uk



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.

Journal Article Type Article
Publication Date Jun 30, 2017
Journal Environmental Modelling and Software
Print ISSN 1364-8152
Electronic ISSN 1364-8152
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 92
APA6 Citation Humphrey, G. B., Maier, H. R., Wu, W., Mount, N. J., Dandy, G. C., Abrahart, R., & Dawson, C. (2017). Improved validation framework and R-package for artificial neural network models. Environmental Modelling and Software, 92, doi:10.1016/j.envsoft.2017.01.023
DOI https://doi.org/10.1016/j.envsoft.2017.01.023
Keywords Artificial neural networks; Multi-layer perceptron; R-package; Structural validation; Replicative validation; Predictive validation
Publisher URL http://www.sciencedirect.com/science/article/pii/S136481521630963X
Copyright Statement Copyright information regarding this work can be found at the following address: http://creativecommons.org/licenses/by-nc-nd/4.0

Files

ValidationFramework_HRM.pdf (3.2 Mb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://creativecommons.org/licenses/by-nc-nd/4.0





You might also like



Downloadable Citations

;