Enhancing Near Real Time AI-NWP Hurricane Forecasts: Improving Explainability and Performance Through Physics-Based Models and Land Surface Feedback

TL;DR

This paper explores how incorporating land surface feedback into AI-based hurricane forecast models improves their accuracy and explainability by demonstrating the significant impact of land-atmosphere interactions on storm trajectories.

Contribution

The study introduces the importance of land surface interactions in AI-NWP hurricane forecasts and demonstrates how physics-based land feedback can enhance model performance and explainability.

Findings

Land surface conditions significantly influence hurricane paths.

Inclusion of land feedback improves forecast accuracy.

Physics-based land interactions are crucial for reliable hurricane prediction.

Abstract

Hurricane track forecasting remains a significant challenge due to the complex interactions between the atmosphere, land, and ocean. Although AI-based numerical weather prediction models, such as Google Graphcast operation, have significantly improved hurricane track forecasts, they currently function as atmosphere-only models, omitting critical land and ocean interactions. To investigate the impact of land feedback, we conducted independent simulations using the physics-based Hurricane WRF experimental model to assess how soil moisture variations influence storm trajectories. Our results show that land surface conditions significantly alter storm paths, demonstrating the importance of land-atmosphere coupling in hurricane prediction. Although recent advances have introduced AI-based atmosphere-ocean coupled models, a fully functional AI-driven atmosphere-land-ocean model does not yet exist. Our findings suggest that AI-NWP models could be further improved by incorporating land surface interactions, improving both forecast accuracy and explainability. Developing a fully coupled AI-based weather model would mark a critical step toward more reliable and physically consistent hurricane forecasting, with direct applications for disaster preparedness and risk mitigation.