arXiv subjects

Stjepan Marcelja

Publications and source records attributed to Stjepan Marcelja.

3 recordsLinked to original sources

arXiv2026

Winter forecasting of September/October rainfall

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.

physics.ao-ph↗

arXiv2024

Forecasting seasonal rainfall in SE Australia using Empirical Orthogonal Functions and Neural Networks

Quantitative forecasting of average rainfall into the next season remains highly challenging, but in some favourable isolated cases may be possible with a series of relatively simple steps. We chose to explore predictions of austral springtime rainfall in SE Australia regions based on the surrounding ocean surface temperatures during the winter. In the first stage, we search for correlations between the target rainfall and both the standard ocean climate indicators as well as the time series of surface temperature data expanded in terms of Empirical Orthogonal Functions (EOFs). In the case of the Indian Ocean, during the winter the dominant EOF shows stronger correlation with the future rainfall than the commonly used Indian Ocean Dipole. Information sources with the strongest correlation to the historical rainfall data are then used as inputs into deep learning artificial neural networks. The resulting hindcasts appear accurate for September and October and less reliable for November. We also attempt to forecast the rainfall in several regions for the coming austral spring.

physics.ao-ph↗

arXiv2022

Strengthening of Indian Ocean teleconnections permits predictions of springtime rainfall in SE Australia

Rainy years and dry years in SE Australia are known to be correlated with sea surface temperatures in the specific areas of the Indian Ocean. While over the past 100 years the correlation had been both positive and negative, it significantly increased in strength since the beginning of the 21st century. Over this period, Indian Ocean sea surface temperatures during the winter months, together with the El Niño variations, contain sufficient information to accurately hindcasts springtime rainfall in SE Australia. Using deep learning neural networks trained on the early 21st century data we performed both hindcasting and simulated forecasting of the recent spring rainfall in SE Australia, Victoria and South Australia. The method is particularly suitable for quantitative testing of the importance of different ocean regions in improving the predictability of rainfall modelling. The network hindcasting results with longer lead times are improved when current winter El Niño temperatures in the input are replaced by forecast temperatures from the best dynamical models. High skill is limited to the rainfall forecasts for the September/October period constructed from the end of June.

physics.ao-ph↗