Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/25254

Title: Improved validation framework and R-package for artificial neural network models
Authors: Humphrey, Greer B.
Maier, Holger R.
Wu, Wenyan
Mount, Nick J.
Dandy, Graeme C.
Abrahart, Robert J.
Dawson, Christian W.
Keywords: Artificial neural networks
Multi-layer perceptron
R-package
Structural validation
Replicative validation
Predictive validation
Issue Date: 2017
Publisher: © Elsevier
Citation: HUMPHREY, G.B. ...et al., 2017. Improved validation framework and R-package for artificial neural network models. Environmental Modelling and Software, 92, pp. 82-106.
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.
Description: This paper is in closed access.
Version: Published
DOI: 10.1016/j.envsoft.2017.01.023
URI: https://dspace.lboro.ac.uk/2134/25254
Publisher Link: https://doi.org/10.1016/j.envsoft.2017.01.023
ISSN: 1364-8152
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
Humphrey et al 2017 EMS ANN Validation 1-s2.0-S136481521630963X-main.pdfPublished version4.01 MBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.