Darwen, Paul J. (2019) The varying success of Bayesian model averaging: an empirical study of flood prediction. In: Proceedings of the IEEE Symposium Series on Computational Intelligence. pp. 1764-1771. From: SSCI 2018: IEEE Symposium Series on Computational Intelligence, 18-21 November 2018, Bengalaru, India.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Bayesian model averaging attempts to find the most probable prediction, in contrast to finding the prediction of the single best-fit, most probable model. Using an example problem of predicting floods in five intermittent rivers in the Australian outback, this paper establishes that the improvement in prediction accuracy from Bayesian model averaging correlates with the size of the difference in the prediction between Bayesian model averaging and the single best-fit model.

Item ID:	57846
Item Type:	Conference Item (Research - E1)
ISBN:	978-1-5386-9276-9
Keywords:	Bayesian model averaging, streamflow prediction, variational models
Date Deposited:	03 Apr 2019 23:27
FoR Codes:	46 INFORMATION AND COMPUTING SCIENCES > 4603 Computer vision and multimedia computation > 460307 Multimodal analysis and synthesis @ 90% 49 MATHEMATICAL SCIENCES > 4905 Statistics > 490510 Stochastic analysis and modelling @ 10%
SEO Codes:	83 ANIMAL PRODUCTION AND ANIMAL PRIMARY PRODUCTS > 8304 Pasture, Browse and Fodder Crops > 830403 Native and Residual Pastures @ 70% 96 ENVIRONMENT > 9609 Land and Water Management > 960913 Water Allocation and Quantification @ 30%
Downloads:	Total: 1
	More Statistics