A Land Of Droughts And Flooding Rains: Forecasting Rainfall At Long Lead Times

The IPA has today released a new research paper by Senior Fellow, Dr John Abbot, highlighting the recurrent patterns of drought and flooding rains in Australia – challenging claims that recent weather events were unprecedented – and exploring the potential of AI techniques to provide more skilful long-lead monthly forecasts than those provided by the Bureau of Meteorology’s GCM models, using rainfall patterns in Gympie, Queensland, as a case study.

Download A Land Of Droughts and Flooding Rains: Forecasting Rainfall At Long Lead Times, here.

The Australian continent has a long history of droughts and floods, extending into recent years. At any particular time, there is often a drought somewhere in continent of Australia. However, there is often a reluctance to acknowledge drought as a persistent aspect of Australian life and the arrival of drought is often greeted with surprise with a tendency for each drought to be perceived as “the worst on record”. Droughts are a recurrent and natural part of the Australian climate, with evidence of drought dating back thousands of years. The impacts of droughts have been categorised as meteorological, hydrological, agricultural, and socioeconomic. Many of the reported studies have emphasised the impact of drought on agriculture, which is as topical as ever due to drought in parts of eastern Australia affecting farming communities.

Flooding rains are also a recurring feature of the Australian climate. For example, prolonged rainfall over large areas of Queensland led to flooding of historic proportions in December 2010, extending into January 20115. About 33 people died as a result of those floods, with more than 78% of the state (an area larger than France and Germany combined) declared a disaster zone. More than 2.5 million people were affected5 with approximately 29,000 homes and businesses experiencing some form of inundation, with the cost of flooding estimated to be over A$5 billion. In January 2011, More recently in 2022, extreme rainfall conditions in New South Wales and south-east Queensland have again caused major floods affecting thousands of properties.

Climate indices and oscillations such as ENSO are often used in constructing models that attempt to forecast rainfall. The need to improve rainfall forecasts has again been highlighted by the recent extreme rainfall and floods in eastern Australia. Techniques that depend on artificial intelligence (AI) methods such as machine learning have been extensively developed during the past decade around the world and reported in the scientific literature, but are not utilised to produce official forecasts for example by the Australian Bureau of Meteorology (BOM). The application of AI through artificial neural networks (ANNs) is illustrated in this report for the town of Gympie, which was severely affected by the recent flooding events.

The Tonga volcanic eruption of 2022 has been confirmed as the largest explosive eruption of the 21st century, and on par with the biggest eruptions ever recorded and possible influences on climate have been discussed by the BOM. Its influence on rainfall over eastern Australia in February 2022 would be regarded as a sporadic event, not predicted in ANN rainfall forecasts for Gympie with lead times in the range 12 months to 60 months.

Download A Land Of Droughts and Flooding Rains: Forecasting Rainfall At Long Lead Times, here.