GeoXplain: On-the-Fly Visual Explanations for Weather Foundation Models

2026-07-06

AI Summary

This work addresses the challenge of interpreting high-dimensional forecasts from foundation models for weather and climate, which static visualizations fail to adequately reveal. To this end, we propose the first general-purpose explainability framework tailored for Earth system models, accompanied by an interactive Python visualization toolkit. The toolkit enables dynamic exploration of attribution maps across meteorological variables, pressure levels, and forecast lead times within both map and globe views, featuring synchronized timelines, target annotations, and overlays of physical fields such as ERA5 reanalysis data. Integrating multiple attribution methods—including gradient saliency, Integrated Gradients, RISE, and ViT-CX—it supports unified deployment via Jupyter widgets and a browser-based frontend, compatible with both local environments and SLURM cluster backends. The open-source package is available via PyPI, significantly enhancing the interpretability and analytical efficiency of AI-driven meteorological models.

Abstract

Weather and climate foundation models produce high-dimensional forecasts whose learned relationships are difficult to inspect with static plots alone. GeoXplain is an interactive Python-based visualization toolkit for exploring geospatial attribution maps across climate variables, atmospheric pressure levels, and forecast time. The toolkit accepts attribution bundles containing attribution grids together with corresponding metadata and renders them in a notebook widget or browser with map and globe modes, linked timelines, pressure-level controls, target annotations, and optional physical-field overlays. We frame GeoXplain as a model-agnostic earth-system visualization toolkit and present the GeoXplain Aurora Adapter as its first computation backend. The adapter computes explanations for the Aurora foundation model, either in a local GPU process, through a GPU listener, or through a SLURM-backed listener, while preserving the same Python call site for analysts. It currently supports gradient saliency, Integrated Gradients, RISE, ViT-CX, multi-frame saliency and Integrated Gradients rollouts, and retrieval of ERA5 overlays. GeoXplain can be installed as a PyPI package with pip install geoxplain. The code is open-source and available at https://github.com/clemenskoprolin/geoxplain.

Problem

• weather foundation models
• geospatial attribution
• visual explanations
• interactive visualization
• model interpretability

Innovation

• interactive visualization
• attribution maps
• foundation models
• model interpretability
• geospatial analysis