Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization
Abbot, John, and Marohasy, Jennifer (2017) Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization. Atmospheric Research, 197. pp. 289-299.
PDF (Published Version)
- Published Version
Restricted to Repository staff only |
Abstract
General circulation models, which forecast by first modelling actual conditions in the atmosphere and ocean, are used extensively for monthly rainfall forecasting. We show how more skilful monthly and seasonal rainfall forecasts can be achieved through the mining of historical climate data using artificial neural networks (ANNs). This technique is demonstrated for two agricultural regions of Australia: the wheat belt of Western Australia and the sugar growing region of coastal Queensland. The most skilful monthly rainfall forecasts measured in terms of Ideal Point Error (IPE), and a score relative to climatology, are consistently achieved through the use of ANNs optimized for each month individually, and also by choosing to input longer historical series of climate indices. Using the longer series restricts the number of climate indices that can be used.
Item ID: | 51327 |
---|---|
Item Type: | Article (Research - C1) |
ISSN: | 1873-2895 |
Funders: | B. Macfie Family Foundation |
Date Deposited: | 25 Oct 2017 07:41 |
FoR Codes: | 37 EARTH SCIENCES > 3701 Atmospheric sciences > 370108 Meteorology @ 100% |
SEO Codes: | 96 ENVIRONMENT > 9602 Atmosphere and Weather > 960203 Weather @ 100% |
Downloads: |
Total: 1 |
More Statistics |