Earth Science Foundation Models: From Perception to Reasoning and Discovery

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Xiangyu, Liu, Bo, Zhang, Yuehan, Song, Zelin, Xu, Wanghan, Liu, Feng, Wang, Fengxiang, Fei, Ben, Ling, Fenghua, Wei, Wangxu, Zhang, Wenlong, Wu, Xiao-Ming
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911676951953408
author Zhao, Xiangyu
Liu, Bo
Zhang, Yuehan
Song, Zelin
Xu, Wanghan
Liu, Feng
Wang, Fengxiang
Fei, Ben
Ling, Fenghua
Wei, Wangxu
Zhang, Wenlong
Wu, Xiao-Ming
author_facet Zhao, Xiangyu
Liu, Bo
Zhang, Yuehan
Song, Zelin
Xu, Wanghan
Liu, Feng
Wang, Fengxiang
Fei, Ben
Ling, Fenghua
Wei, Wangxu
Zhang, Wenlong
Wu, Xiao-Ming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12542
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Earth Science Foundation Models: From Perception to Reasoning and Discovery
Zhao, Xiangyu
Liu, Bo
Zhang, Yuehan
Song, Zelin
Xu, Wanghan
Liu, Feng
Wang, Fengxiang
Fei, Ben
Ling, Fenghua
Wei, Wangxu
Zhang, Wenlong
Wu, Xiao-Ming
Instrumentation and Methods for Astrophysics
Earth and Planetary Astrophysics
Machine Learning
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.
title Earth Science Foundation Models: From Perception to Reasoning and Discovery
topic Instrumentation and Methods for Astrophysics
Earth and Planetary Astrophysics
Machine Learning
url https://arxiv.org/abs/2605.12542