Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems

2026-09-08

AI Summary

本文提出了一种用于地球系统模拟的行动条件世界建模框架，通过过渡-行动预训练和掩码响应学习方法，实现可控状态转换学习，以解决现有模拟器无法进行用户指定干预的问题。

Abstract

Machine learning emulators have become essential for accelerating expensive Earth-system simulations, but most existing approaches remain passive forecasters: they reproduce simulator trajectories under prescribed forcings without an explicit interaction mechanism for user-specified interventions. This limits their use in interactive scientific workflows and Earth-system digital twins, where users often need to explore how a system would respond if selected state components were changed. We propose an action-conditioned world-modeling framework for Earth-system emulation that reformulates simulator trajectories as supervision for controllable state-transition learning. The key idea is transition-action pretraining: naturally observed state changes are treated as label-free action supervision, allowing the model to learn both prescribed dynamics and action-conditioned responses without manually annotated interventions. We further introduce masked response learning to infer unobserved variables under partial state edits and learn coupled system dependencies. We test this framework on ecosystem dynamics across six global regions and multiple stand ages. Experiments show that the model preserves competitive long-horizon emulation accuracy while enabling controllable structural interventions and coherent responses in coupled ecosystem-cycle variables. These results suggest a practical route from passive Earth-system emulators toward interactive, intervention-aware scientific surrogates.

Problem

• Earth-system simulations
• interactive scientific workflows
• user-specified interventions
• passive forecasters
• state transitions

Innovation

• action-conditioned world-modeling
• transition-action pretraining
• masked response learning