Seasonal Climate

Seasonal climate prediction aims to forecast weather patterns months in advance, supporting crucial decision-making in sectors like agriculture and energy. Current research heavily utilizes machine learning, particularly deep learning architectures like UNet++ and novel neural network designs, to improve the accuracy of these forecasts by leveraging coupled ocean-atmosphere dynamics and incorporating data from climate models (like CMIP6) and reanalysis datasets (like ERA5). These advancements lead to more reliable predictions, reducing forecast errors and improving resource management, particularly in predicting temperature anomalies with better accuracy during summer months compared to winter. The improved accuracy of these models has significant implications for mitigating the impacts of extreme weather events and enhancing societal resilience.

Papers

June 12, 2024

Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model
Chenggong Wang, Michael S. Pritchard, Noah Brenowitz, Yair Cohen, Boris Bonev, Thorsten Kurth, Dale Durran, Jaideep Pathak
Earth System Ensemble Forecast Earth System Model Seasonal Climate

September 5, 2023

Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network
Smit Marvaniya, Jitendra Singh, Nicolas Galichet, Fred Ochieng Otieno, Geeth De Mel, Kommy Weldemariam
Time Series Forecasting Demand Forecasting Modular Neural Network Seasonal Climate

February 21, 2023

Climate Model Driven Seasonal Forecasting Approach with Deep Learning
Alper Unal, Busra Asan, Ismail Sezen, Bugra Yesilkaynak, Yusuf Aydin, Mehmet Ilicak, Gozde Unal
Deep Learning Ecmwf Reanalysis V5 Coupled Model Intercomparison Project Seasonal Climate

Seasonal Climate

Papers

Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model

Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network

Climate Model Driven Seasonal Forecasting Approach with Deep Learning