EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting

📄 arXiv: 2606.27277v1 📥 PDF

作者: Junwei Luo, Shuai Yuan, Zhenya Yang, Yansheng Li, Zhe Liu, Hengshuang Zhao

分类: cs.AI, cs.CV

发布日期: 2026-06-25

备注: 28 pages, 5 figures, 11 tables

🔗 代码/项目: GITHUB


💡 一句话要点

提出EO-WM以解决气象驱动的地球观测预测问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)

关键词: 地球观测 气象预测 视频扩散 物理建模 植被指数 不确定性建模 气候变化 生态监测

📋 核心要点

  1. 现有方法未能充分考虑气象变化对地表动态预测的影响,导致预测结果的不确定性较高。
  2. EO-WM通过物理信息的条件框架,将气象因素分为气候基线、天气异常和累积物理压力信号,从而更准确地建模气象影响。
  3. 实验结果表明,EO-WM在预测归一化植被指数(NDVI)下降幅度方面相较于基线减少了5.63%的误差,并提高了方向命中率7.80%。

📝 摘要(中文)

地球观测(EO)预测旨在根据卫星观测数据预测未来的地表动态,尤其是在气象条件变化的情况下。本文将这一任务视为一个部分观测的、气象驱动的世界建模问题,气象作为条件信号,而由于观测稀疏和未观测的地表状态,预测仍然存在不确定性。现有方法未能充分捕捉这一设置:确定性模型将不确定性压缩为单一的未来预测,而基于扩散的方法通常将气象变量视为未区分的条件信号。我们提出了EO-WM,一个用于多光谱EO预测的视频扩散变换器,结合了物理信息的条件框架,能够更好地捕捉气象对地表动态的影响。

🔬 方法详解

问题定义:本文旨在解决气象驱动的地球观测预测中的不确定性问题。现有方法往往将气象因素视为单一信号,未能有效捕捉其对预测结果的影响。

核心思路:EO-WM通过物理信息的条件框架,将气象因素细分为气候基线和天气异常,利用不同的条件路径来处理这些因素,从而更好地反映气象变化对地表动态的影响。

技术框架:EO-WM的整体架构包括多个模块:首先是气象数据的预处理模块,其次是基于视频扩散的预测模块,最后是结果评估模块,确保模型能够有效响应气象变化。

关键创新:EO-WM的主要创新在于其物理信息的条件框架,能够将气象因素的影响分开处理,并通过时间累积异常信号来捕捉持续的热量和干旱压力,这与现有方法的单一处理方式有本质区别。

关键设计:在模型设计中,采用了特定的损失函数来优化预测准确性,并通过多路径条件输入来增强模型对气象变化的响应能力。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,EO-WM在预测归一化植被指数(NDVI)下降幅度方面相较于基线减少了5.63%的误差,方向命中率提高了7.80%。这些结果表明,EO-WM在标准像素级指标上仍具竞争力,同时在气象响应行为上表现出色。

🎯 应用场景

该研究在气象驱动的地球观测预测领域具有广泛的应用潜力,尤其是在农业、生态监测和气候变化研究等领域。通过提高预测的准确性和响应能力,EO-WM能够为决策者提供更可靠的数据支持,帮助应对气候变化带来的挑战。

📄 摘要(原文)

Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions. In this paper, we view this task as a partially observed, weather-driven world modeling problem, in which weather acts as a conditioning signal, while forecasting remains uncertain due to sparse observations and unobserved land-surface states. However, existing methods do not fully capture this setting: deterministic models collapse uncertainty into a single future prediction, while diffusion-based methods typically treat weather variables as undifferentiated conditioning signals, and existing benchmarks focus mainly on reconstruction accuracy rather than whether forecasts respond correctly to changed weather forcing.We introduce EO-WM, a video diffusion transformer for multispectral EO forecasting. EO-WM incorporates a physically informed conditioning framework that represents meteorological forcing through a climatological baseline, weather anomalies, and cumulative physical stress signals. Specifically, it separates baseline and anomaly through distinct conditioning pathways, and accumulates anomalous forcing over time to capture sustained heat and drought stress. To evaluate weather-response behavior beyond standard metrics, we introduce two diagnostic benchmarks: an Extreme Summer Benchmark for severity-aware prediction of vegetation degradation under extreme weather, and a Seasonal Matched-Pair Benchmark for testing response fidelity under changed weather forcing. Experiments show that EO-WM reduces the error in predicted Normalized Difference Vegetation Index (NDVI) decline amplitude by a relative 5.63% and improves directional hit rate by a relative 7.80%, while remaining competitive on standard pixel-level metrics. The benchmarks and model will be made open-source at https://github.com/Luo-Z13/EO-WM.