This study builds on the E-CONTRAIL project’s methodologies to improve regional climate forecasting through advanced deep-learning techniques. We evaluate 32 CMIP6 models using a Deep Learning-TOPSIS (DL-TOPSIS) ranking system and refine the best-performing models with high-resolution downscaling. Using state-of-the-art deep-learning architectures, including GeoSTANet, ViT, CNN-LSTM, and ConvLSTM, we enhance temperature extreme predictions. Our results confirm that transformer-based approaches outperform traditional methods, demonstrating the adaptability of E-CONTRAIL techniques for broader climate modeling applications.
Parthiban Loganathan, Elias Zea, Ricardo Vinuesa, Evelyn Otero. Regional climate projections using a Deep Learning-based model-ranking and downscaling framework: Application to European climate zones. Environmental Science and Pollution Research (ESPR) (under review), 2025. Preprint available @ arXiv:2502.20132
Abstract
Accurate regional climate forecast calls for high-resolution downscaling of Global Climate Models (GCMs). This work presents a deep-learning-based multi-model evaluation and downscaling framework ranking 32 Coupled Model Intercomparison Project Phase 6 (CMIP6) models using a Deep Learning-TOPSIS (DL-TOPSIS) mechanism and so refines outputs using advanced deep-learning models. Using nine performance criteria, five Köppen-Geiger climate zones -- Tropical, Arid, Temperate, Continental, and Polar -- are investigated over four seasons. While TaiESM1 and CMCC-CM2-SR5 show notable biases, ranking results show that NorESM2-LM, GISS-E2-1-G, and HadGEM3-GC31-LL outperform other models. Four models contribute to downscaling the top-ranked GCMs to 0.1∘ resolution: Vision Transformer (ViT), Geospatial Spatiotemporal Transformer with Attention and Imbalance-Aware Network (GeoSTANet), CNN-LSTM, and CNN-Long Short-Term Memory (ConvLSTM). Effectively capturing temperature extremes (TXx, TNn), GeoSTANet achieves the highest accuracy (Root Mean Square Error (RMSE) = 1.57∘C, Kling-Gupta Efficiency (KGE) = 0.89, Nash-Sutcliffe Efficiency (NSE) = 0.85, Correlation (r) = 0.92), so reducing RMSE by 20% over ConvLSTM. CNN-LSTM and ConvLSTM do well in Continental and Temperate zones; ViT finds fine-scale temperature fluctuations difficult. These results confirm that multi-criteria ranking improves GCM selection for regional climate studies and transformer-based downscaling exceeds conventional deep-learning methods. This framework offers a scalable method to enhance high-resolution climate projections, benefiting impact assessments and adaptation plans.
Comments