Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion
This work addresses reliability issues in climate prediction for disaster risk management, but it is incremental as it builds on existing fusion and normalization techniques.
The paper tackles model uncertainty in long-range climate forecasting by proposing a late fusion approach that combines multiple models to reduce errors, showing improved accuracy over 30-year climate normals in 2m temperature forecasting, with performance increasing as more models are added.
Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property. Accurate long-range climate prediction allows more time for preparation and disaster risk management for such extreme events. Although machine learning approaches have shown promising results in long-range climate forecasting, the associated model uncertainties may reduce their reliability. To address this issue, we propose a late fusion approach that systematically combines the predictions from multiple models to reduce the expected errors of the fused results. We also propose a network architecture with the novel denormalization layer to gain the benefits of data normalization without actually normalizing the data. The experimental results on long-range 2m temperature forecasting show that the framework outperforms the 30-year climate normals, and the accuracy can be improved by increasing the number of models.