Author(s)

J. Abbot, J. Marohasy

Abstract

The Murray Darling Basin accounts for nearly 40% of the value of agricultural production in Australia, and 65% of the irrigated land. We use an artificial neural network (ANN), a form of machine learning, to show the potential for more reliable monthly rainfall forecasts with a lead time of 3 months, and the potential skill of the same model for 6, 9, 12 and 18 month lead-times for the township of Miles, in the northern Basin. The skill of these forecasts is contrasted with the skill of the Predictive Ocean Atmosphere Model for Australia (POAMA), a general circulation model used for operational forecasts by the Australian Bureau of Meteorology. Forecasts from the ANN are significantly more skilful for all lead times. The ANN’s capacity to integrate information from the climate indices Niño 1.2, 3, 3.4 and 4, the Dipole Mode Index (DMI), and also a composite local maximum and minimum atmospheric temperature series, contributes on average approximately 60% of the skill of the ANN forecast.

Keywords

rainfall, forecasting, artificial neural network, Murray Darling Basin