Winter forecasting of September/October rainfall

TL;DR

This study develops a seasonal rainfall prediction method using low-dimensional nonlinear forecasting with deep neural networks, incorporating Indian-Pacific Ocean variability to improve September/October rainfall forecasts in southeastern Australia.

Contribution

It introduces a novel approach combining reduced-order modeling and deep learning to forecast seasonal rainfall based on coupled ocean variability.

Findings

High agreement between forecasts and observed rainfall data

Validates the hypothesis of chaotic but predictable rainfall dynamics

Demonstrates effectiveness of the method for seasonal forecasting

Abstract

We formulate seasonal rainfall prediction as a reduced-order nonlinear forecasting problem, embedding coupled Indian-Pacific Ocean variability into a low-dimensional state space and projecting it forward using deep neural networks. Variables include Nino 3.4, the Indian Ocean Dipole (IOD), the Indian Ocean meridional SST gradient, and selected empirical orthogonal functions. Monthly time series of the variables then form the input into deep neural networks which project rainfall further into the future. Forecasts for the 2025 austral spring were generated and archived in the Mendeley database during the winter. Subsequent rainfall data demonstrated a high level of agreement with the forecasts, providing a validation of the method and supporting the hypothesis that chaotic yet conditionally predictable dynamics underpin spring rainfall variability in southeastern Australia.