Johans Utama

Deep Learning-Based Meteorological Data Downscaling: A Comparative Study with Physics-Informed CNN and a Component-Level Ablation Analysis

The proposed Physics-Informed CNN (PICNN), which integrates multi-scale feature extraction, spatial attention mechanisms, and a composite physics-informed loss function incorporating mean squared error, Laplacian spatial smoothness regularization, and spatial energy conservation constraints, achieves the best performan...