Beyond Mean Squared Error: Alternative Loss Functions for Geoscience Image Regression with Neural Networks

The paper proposes using alternative loss functions beyond mean squared error (MSE) for geoscience image regression tasks with neural networks. The limitations of MSE for capturing spatial correlation and overall distribution are discussed. Loss functions incorporating earth mover’s distance, Pearson Correlation Coefficient, and selective input-driven weighting are presented. Experiments applying these to a passive microwave brightness temperature emulation task demonstrate improved performance over MSE baseline for preserving spatial patterns and distributions. The input-driven loss function utilizing the solar angle showed the greatest improvement in mean absolute error. Overall, the results demonstrate the importance of selecting appropriate loss functions in geoscience regression models to better capture physical properties.