Artificial neural networks for prediction of Steadman Heat Index

Chand, Bhuwan and Nguyen-Huy, Thong ORCID: https://orcid.org/0000-0002-2201-6666 and Deo, Ravinesh C. ORCID: https://orcid.org/0000-0002-2290-6749 (2021) Artificial neural networks for prediction of Steadman Heat Index. In: Intelligent data analytics for decision-support systems in hazard mitigation: theory and practice of hazard mitigation. Springer Transactions in Civil and Environmental Engineering. Springer, Singapore, pp. 293-357. ISBN 978-981-15-5771-2


Abstract

This chapter aims to design and evaluate Artificial Neural Networks (ANN), an intelligent data analytic model to predict daily Steadman Heat Index (SHI) using temperature and humidity. Using 15 stations in Australia, trend analysis for the period 1950–2017 is performed using Mann–Kendal test statistics Sen’s slope methods. Twelve ANN models are developed with a three-layer network employing different combinations of the training algorithm, hidden transfer, and output function. The Levenberg–Marquardt and Broyden–Fletcher–Goldfarb–Shanno (BFGS) quasi-Newton backpropagation algorithms are utilized to determine the best combination of learning algorithms, hidden transfer, and output functions of the optimum ANN model. Assessment of model performance includes the spread and distribution of predicted SHI, Legates and McCabe Index, Mean Absolute Error, Root Mean Square Error, Coefficient of Determination, the Willmott’s Index of Agreement, and Nash–Sutcliffe Coefficient of Efficiency. The designed model appears to be a suitable intelligent data analytic tool for weather prediction, climate change studies, and probable evaluation of dry climatic conditions in the near future replying to historical datasets to model their future values. The findings have implications for disaster risk management particularly mitigating heatwave risk and consequences on human populations, ecosystems, and other areas including agricultural, health, and wellbeing.


Statistics for USQ ePrint 39217
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Additional Information: Permanent restricted access to Published chapter in accordance with the copyright policy of the publisher.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 -)
Faculty/School / Institute/Centre: Current - Institute for Life Sciences and the Environment - Centre for Applied Climate Sciences (1 Aug 2018 -)
Date Deposited: 02 Sep 2020 01:36
Last Modified: 02 Sep 2020 02:21
Uncontrolled Keywords: data-driven; artificial neural networks; heatwaves prediction; backpropagation algorithms; hidden transfer
Fields of Research (2008): 05 Environmental Sciences > 0502 Environmental Science and Management > 050204 Environmental Impact Assessment
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080110 Simulation and Modelling
Fields of Research (2020): 41 ENVIRONMENTAL SCIENCES > 4104 Environmental management > 410402 Environmental assessment and monitoring
46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460207 Modelling and simulation
Socio-Economic Objectives (2008): E Expanding Knowledge > 97 Expanding Knowledge > 970105 Expanding Knowledge in the Environmental Sciences
Identification Number or DOI: https://doi.org/10.1007/978-981-15-5772-9_16
URI: http://eprints.usq.edu.au/id/eprint/39217

Actions (login required)

View Item Archive Repository Staff Only