# Strategic Governance of AI Models in Earth Science

arXiv: https://arxiv.org/abs/2610.10560 · HTML: https://mlsanity.com/paper/2610.10560/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 56 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [FuXi: A cascade machine learning forecasting system for 15-day global weather forecast](https://mlsanity.com/paper/2306.12873/) (2023)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast](https://mlsanity.com/paper/2211.02556/) (2022)
- [LoRA vs Full Fine-tuning: An Illusion of Equivalence](https://mlsanity.com/paper/2410.21228/) (2024)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science](https://mlsanity.com/paper/2303.00652/) (2023)
- [Dynamical Tests of a Deep-Learning Weather Prediction Model](https://mlsanity.com/paper/2309.10867/) (2023)
- [How Good Are LLMs at Out-of-Distribution Detection?](https://mlsanity.com/paper/2308.10261/) (2023)
- [Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features](https://mlsanity.com/paper/2512.24440/) (2025)
- [No One Knows the State of the Art in Geospatial Foundation Models](https://mlsanity.com/paper/2605.12678/) (2026)
- [ADAM-SINDy: An Efficient Optimization Framework for Parameterized Nonlinear Dynamical System Identification](https://mlsanity.com/paper/2410.16528/) (2024)
- [Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging](https://mlsanity.com/paper/2407.06100/) (2024)
- [Recommendations for Comprehensive and Independent Evaluation of Machine Learning-Based Earth System Models](https://mlsanity.com/paper/2410.19882/) (2024)
- [Training Data Attribution (TDA): Examining Its Adoption & Use Cases](https://mlsanity.com/paper/2501.12642/) (2025)
- [PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models](https://mlsanity.com/paper/2606.10642/) (2026)
- [Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs](https://mlsanity.com/paper/2605.21602/) (2026)
- [SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators](https://mlsanity.com/paper/2603.20410/) (2026)
- [Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry](https://mlsanity.com/paper/2607.20778/) (2026)

## Abstract (arXiv)

AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their development and adoption are outpacing the scientific community's ability to evaluate them. These models are judged almost entirely by benchmark skill metrics, which measure how closely a forecast reproduces a reference product but not whether a model represents the physical processes governing the system it predicts. Forecast skill and physical reliability are therefore distinct properties. The distinction is most consequential under the nonstationary conditions of a changing climate for which these models were never trained. We identify five priorities for the physical evaluation of AI models in Earth science from task-specific emulators to foundation models, spanning training data, fine-tuning, behavioral testing, mechanistic interpretability, and output validation. We recommend three activities for the coming decade: 1) open AI-ready evaluation datasets, 2) a shared reporting standard for physics-based evaluation, and 3) a dedicated research program on the safety of these models.