KARINA: An Efficient Deep Learning Model for Global Weather Forecast
This work addresses the problem of resource-intensive weather forecasting for climate researchers by offering a more efficient model, though it appears incremental as it builds on existing architectures like ConvNext and SENet.
The paper tackles the high computational cost of deep learning models for global weather prediction by introducing KARINA, which achieves forecasting accuracy comparable to higher-resolution models using only 4 NVIDIA A100 GPUs and less than 12 hours of training, surpassing benchmarks like ECMWF S2S reforecasts at up to 7 days lead time.
Deep learning-based, data-driven models are gaining prevalence in climate research, particularly for global weather prediction. However, training the global weather data at high resolution requires massive computational resources. Therefore, we present a new model named KARINA to overcome the substantial computational demands typical of this field. This model achieves forecasting accuracy comparable to higher-resolution counterparts with significantly less computational resources, requiring only 4 NVIDIA A100 GPUs and less than 12 hours of training. KARINA combines ConvNext, SENet, and Geocyclic Padding to enhance weather forecasting at a 2.5° resolution, which could filter out high-frequency noise. Geocyclic Padding preserves pixels at the lateral boundary of the input image, thereby maintaining atmospheric flow continuity in the spherical Earth. SENet dynamically improves feature response, advancing atmospheric process modeling, particularly in the vertical column process as numerous channels. In this vein, KARINA sets new benchmarks in weather forecasting accuracy, surpassing existing models like the ECMWF S2S reforecasts at a lead time of up to 7 days. Remarkably, KARINA achieved competitive performance even when compared to the recently developed models (Pangu-Weather, GraphCast, ClimaX, and FourCastNet) trained with high-resolution data having 100 times larger pixels. Conclusively, KARINA significantly advances global weather forecasting by efficiently modeling Earth's atmosphere with improved accuracy and resource efficiency.