Maximizing the Impact of Deep Learning on Subseasonal-to-Seasonal Climate Forecasting: The Essential Role of Optimization
Preprint
Abstract
Weather and climate forecasting is vital for sectors such as agriculture and disaster management. Although numerical weather prediction (NWP) systems have advanced, forecasting at the subseasonal-to-seasonal (S2S) scale, spanning 2 to 6 weeks, remains challenging due to the chaotic and sparse atmospheric signals at this interval. Even state-of-the-art deep learning models struggle to outperform simple climatology models in this domain. This paper identifies that optimization, instead of network structure, could be the root cause of this performance gap, and then we develop a novel multi-stage optimization strategy to close the gap. Extensive empirical studies demonstrate that our multi-stage optimization approach significantly improves key skill metrics, PCC and TCC, while utilizing the same backbone structure, surpassing the state-of-the-art NWP systems (ECMWF-S2S) by over \textbf{19-91\%}. Our research contests the recent study that direct forecasting outperforms rolling forecasting for S2S tasks. Through theoretical analysis, we propose that the underperformance of rolling forecasting may arise from the accumulation of Jacobian matrix products during training. Our multi-stage framework can be viewed as a form of teacher forcing to address this issue. Code is available at \url{https://anonymous.4open.science/r/Baguan-S2S-23E7/}Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Learning skillful medium-range global weather forecastingScience, 2023
- Adaptive bias correction for improved subseasonal forecastingNature Communications, 2023
- Implicit learning of convective organization explains precipitation stochasticityProceedings of the National Academy of Sciences, 2023
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- The sub-seasonal to seasonal prediction project (S2S) and the prediction of extreme eventsnpj Climate and Atmospheric Science, 2018
- The quiet revolution of numerical weather predictionNature, 2015
- The NCEP Climate Forecast System Version 2Journal of Climate, 2014
- Evolution of ECMWF sub-seasonal forecast skill scoresQuarterly Journal of the Royal Meteorological Society, 2013
- Fundamentals of Numerical Weather Prediction2011
- Estimating the Uncertainty in a Regional Climate Model Related to Initial and Lateral Boundary ConditionsJournal of Climate, 2005