Earth Science Foundation Models: From Perception to Reasoning and Discovery

TL;DR

This paper reviews the development and application of Earth science foundation models, highlighting their evolution from perception to reasoning, and covering diverse Earth system domains and multimodal data integration.

Contribution

It provides a comprehensive framework for understanding Earth foundation models' capabilities and applications, including a review of datasets, benchmarks, and future challenges.

Findings

Compiled over 200 datasets and benchmarks across Earth science tasks.

Reviewed models' evolution from perception to reasoning and agency.

Identified key challenges like data heterogeneity and model reliability.

Abstract

Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded reanalysis data, diverse geophysical and geochemical observations, and domain-specific text, to support tasks ranging from basic perception to advanced scientific discovery. This paper provides a unified review of Earth science foundation models (Earth FMs) through two complementary dimensions: depth, which traces the evolution of model capabilities from perception to multimodal reasoning and agentic scientific workflows, and breadth, which summarizes their expanding applications across the atmosphere, hydrosphere, lithosphere, biosphere, anthroposphere, and cryosphere, as well as coupled Earth system processes. Using this framework, we review representative multimodal Earth foundation models and compile more than 200 datasets and benchmarks spanning diverse Earth science tasks and modalities. We further discuss key challenges in multimodal data heterogeneity, scientific reliability and continual updating, scalability and sustainability, and the transition from foundation models to agentic and embodied Earth intelligence, and outline future directions toward more integrated, trustworthy, and actionable AI Earth scientists. Overall, this paper offers a structured roadmap for understanding the development of Earth foundation models from both capability depth and application breadth.