2021/07/31 by Stjepan Marčelja, Marcelja, Stjepan
Earth and Planetary Sciences · Environmental Science · #Atmospheric and Oceanic Physics (physics.ao-ph) #Climate variability and models #FOS: Physical sciences #Geological and Geophysical Studies #Geophysics (physics.geo-ph) #Geophysics and Gravity Measurements #Oceanographic and Atmospheric Processes
paper · pdf · doi:10.48550/arxiv.2108.00164
openalex publication_date 2021/07/31 · openalex created_date 2022/08/02 · openalex updated_date 2026/07/28
Rainy years and dry years in SE Australia are known to be correlated with sea\nsurface temperatures in the specific areas of the Indian Ocean. While over the\npast 100 years the correlation had been both positive and negative, it\nsignificantly increased in strength since the beginning of the 21st century.\nOver this period, Indian Ocean sea surface temperatures during the winter\nmonths, together with the El Ni ~no variations, contain sufficient information\nto accurately hindcasts springtime rainfall in SE Australia. Using deep\nlearning neural networks trained on the early 21st century data we performed\nboth hindcasting and simulated forecasting of the recent spring rainfall in SE\nAustralia, Victoria and South Australia. The method is particularly suitable\nfor quantitative testing of the importance of different ocean regions in\nimproving the predictability of rainfall modelling. The network hindcasting\nresults with longer lead times are improved when current winter El Ni ~no\ntemperatures in the input are replaced by forecast temperatures from the best\ndynamical models. High skill is limited to the rainfall forecasts for the\nSeptember/October period constructed from the end of June.\n