# Decision-Oriented Uncertainty Quantification for Risk Control in Earth System Spatiotemporal Foundation Models

arXiv: https://arxiv.org/abs/2609.14821 · HTML: https://mlsanity.com/paper/2609.14821/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization](https://mlsanity.com/paper/1809.05504/) (2018)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [OneForecast: A Universal Framework for Global and Regional Weather Forecasting](https://mlsanity.com/paper/2502.00338/) (2025)
- [AI-GOMS: Large AI-Driven Global Ocean Modeling System](https://mlsanity.com/paper/2308.03152/) (2023)
- [Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models](https://mlsanity.com/paper/2409.19128/) (2024)
- [Less is More: Data Pruning for Faster Adversarial Training](https://mlsanity.com/paper/2302.12366/) (2023)
- [NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation](https://mlsanity.com/paper/2505.21020/) (2025)
- [MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation](https://mlsanity.com/paper/2507.04290/) (2025)
- [CGMatch: A Different Perspective of Semi-supervised Learning](https://mlsanity.com/paper/2503.02231/) (2025)
- [Distilling Time Series Foundation Models for Efficient Forecasting](https://mlsanity.com/paper/2601.12785/) (2026)
- [Advanced Long-term Earth System Forecasting](https://mlsanity.com/paper/2505.19432/) (2025)
- [Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting](https://mlsanity.com/paper/2605.00850/) (2026)
- [RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models](https://mlsanity.com/paper/2605.03821/) (2026)
- [DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting](https://mlsanity.com/paper/2511.16715/) (2025)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)
- [Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models](https://mlsanity.com/paper/2510.04020/) (2025)
- [MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2607.17329/) (2026)
- [Next Generation Active Learning: Mixture of LLMs in the Loop](https://mlsanity.com/paper/2601.15773/) (2026)
- [Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting](https://mlsanity.com/paper/2605.06916/) (2026)
- [Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction](https://mlsanity.com/paper/2606.19642/) (2026)
- [PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting](https://mlsanity.com/paper/2605.08935/) (2026)
- [MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models](https://mlsanity.com/paper/2608.22236/) (2026)
- [Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention](https://mlsanity.com/paper/2604.19530/) (2026)
- [Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels](https://mlsanity.com/paper/2606.02886/) (2026)
- [Decision-Aligned Evaluation of Uncertainty Quantification](https://mlsanity.com/paper/2606.26990/) (2026)

## Abstract (arXiv)

Earth system modeling is shifting from task-specific predictors toward foundation models with general spatiotemporal representation capabilities. Although these models can jointly encode dynamic Earth fields, external forcings, and static geographic context for multistep forecasting, accurate point predictions or statistically calibrated intervals alone are insufficient for high-impact applications such as extremeweather warning, flood control, renewable-energy dispatch, and emergency resource allocation. What matters in practice is whether predictive uncertainty can be translated into reliable decision risk under specific actions, loss functions, and risk preferences. We propose a decision-oriented uncertainty quantification framework for Earth system spatiotemporal foundation models. The framework produces predictive distributions of future states and uses a decision risk adapter to map forecast samples, decision context, and utility functions into action-conditional risks. A utility-aware calibration module further enforces reliability at the downstream decision-loss level rather than only at the forecast-value level. Calibrated risks are then used to select warning, dispatch, inspection, or resource-allocation actions. Compared with the strongest baseline, the proposed method reduces decision regret by 18.7%, lowers the missed-event rate from 14.2% to 9.1%, and improves expected utility by 11.6%, while maintaining 90.4% predictive coverage and reducing decision calibration error from 0.083 to 0.047. These results suggest that decision-oriented uncertainty quantification can improve the robustness and operational value of Earth system foundation models in risk-sensitive applications.