Earth Science

Follow this topic Ask about this topic

Latest papers

23 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

EarthAlign: Learning Language-Aligned Representations of Earth System Data
Oct 10, 2026Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma +4Cross-Modal Representation Learning Multimodal Embedding
Mohamed bin Zayed University of Artificial Intelligence · ADIA Lab · University of California San Diego
ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks
Oct 6, 2026Qi Cheng, Rongchao Dong, Shengyu Chen +8Earth Science Multi-Agent LLM Systems
Rutgers University New Brunswick, NJ · University of Pittsburgh Pittsburgh, PA · University of Minnesota Minneapolis, MN +3
Physically Typed and Geometry-Aware Representations for Earth Foundation Models
Sep 12, 2026Rajiv RanjanGeospatial Foundation Models Geospatial Representation Learning
Plaksha University
MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity
Sep 2, 2026Yiran Zhang, Jinwen Liu, Daniel Su +7Geospatial Reasoning Evidence-Grounded Generation
1The University of Western Australia · 2Wilfrid Laurier University
Climate Physics Dynamic Matching
Aug 27, 2026Gurjeet Sangra Singh, Frantzeska Lavda, Alexandros KalousisWeather Forecasting Physics-Informed Generative Modeling
University of Geneva, Geneva, Switzerland · HES-SO Geneva, Geneva, Switzerland
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
Aug 24, 2026Zhiqing Cui, Xinxiang Yin, Yihong Tang +11AI Agent Benchmarks Earth Science
NUIST · HKU · McGill +7
HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience
Aug 14, 2026Ziqi Song, Zongyuan Xiang, James G. Ogg +12Earth Science Document Information Extraction
Research Center for Computational Earth and Space Science, Zhejiang Laboratory, Hangzhou, China · School of Electrical & Computer Engineering, Purdue University, Indiana, USA · Zhejiang Deep-time Digital Earth International Research Center, Hangzhou, China +3
Earth Embeddings
Aug 4, 2026Adam J. Stewart, Heng Fang, Isaac A. Corley +1Geospatial Representation Learning Land Cover Classification
Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · KTH Royal Institute of Technology, Stockholm, Sweden +1
PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling
Jul 22, 2026Shiyuan Luo, Runlong Yu, Chonghao Qiu +6Time Series Forecasting Adaptive Retrieval
University of Pittsburgh · University of Alabama · University of Minnesota +3
Bringing Agentic Search to Earth Observation Data Discovery
Jul 2, 2026Minghan Yu, Youran Sun, Chugang Yi +2Agentic Search Remote Sensing
University of Maryland, College Park · University of Florida
EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation
Jul 2, 2026Mahyar Ghazanfari, Amin Tabrizian, Armin Mehrabian +1Multi-Agent LLM Systems LLM Grounding
George Washington University, Washington, DC, USA · NASA Goddard Space Flight Center, Greenbelt, MD, USA · ADNET Systems, Inc., Bethesda, MD, USA
TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?
Jun 11, 2026Dat Tien Nguyen, Thao Nguyen, Fadillah Adamsyah Maani +5Spatial Reasoning Scientific Reasoning
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · ADIA Lab, Abu Dhabi, UAE
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
May 24, 2026Chenyou Guo, Zongqi Liu, Yizhou Zhang +2Scientific Reasoning LLM Fine-Tuning
Ocean University of China · Peking University · Monash University
KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science
May 18, 2026Ziwei Li, Liujun Zhu, Yuchen Liu +5AI for Science Earth Science
State Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing 210098, China · Yangtze Institute for Conservation and Development, Hohai University, Nanjing 210098, China · Meta Platforms Inc. +3
GeoR-Bench: Evaluating Geoscience Visual Reasoning
May 12, 2026Yushuo Zheng, Zicheng Zhang, Huiyu Duan +7Remote Sensing Image Understanding Geospatial Reasoning
Shanghai Jiao Tong University · Beijing University of Technology
Earth Science Foundation Models: From Perception to Reasoning and Discovery
May 9, 2026Xiangyu Zhao, Bo Liu, Yuehan Zhang +9AI for Science Geospatial Foundation Models
Shanghai Artificial Intelligence Laboratory, Shanghai, China
Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges
Apr 5, 2026Rong Lu, Hao Liu, Song HouEarth Science Text Classification
GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation
Mar 26, 2026Jianbo Qi, Mengyao Li, Baogui Jiang +3Geospatial Representation Learning Remote Sensing
Advanced Interdisciplinary Institute of Satellite Applications, Beijing Normal University, Beijing 100875, China · State Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
EVE: A Domain-Specific LLM Framework for Earth Intelligence
Mar 20, 2026Àlex R. Atrio, Antonio Lopez, Jino Rohit +6Earth Science LLM Evaluation
Pi School · Mistral AI · Translated +1
GEAR: Geography-knowledge Enhanced Analog Recognition Framework in Extreme Environments
Mar 19, 2026Zelin Liu, Bocheng Li, Yuling Zhou +5Earth Science Analogical Reasoning
Shanghai Jiao Tong University
GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
Mar 10, 2026Jie Li, Qishun Yang, Nuo LiEarth Science Transformer Attention
College of Petroleum, China University of Petroleum-Beijing at Karamay, Karamay 834000, China
A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
Feb 24, 2026Dmitrii Pantiukhin, Ivan Kuznetsov, Boris Shapkin +3Earth Science Data Analysis Agents
Alfred Wegener Institute for Polar and Marine Research, Bremerhaven, Germany
Towards LLM Agents for Earth Observation
Apr 16, 2025Chia Hsiang Kao, Wenting Zhao, Cheryl Lam +10Code Generation LLM Agent Evaluation
Cornell University · Columbia University

Oct 10, 2026J/K move · Enter open · S save

EarthAlign: Learning Language-Aligned Representations of Earth System Data

Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma, Dat Tien Nguyen+3

Mohamed bin Zayed University of Artificial Intelligence · ADIA Lab · University of California San Diego

Cross-Modal Representation Learning Multimodal Embedding Earth Science Cross-Modal Retrieval

Open paper AskPDF arXiv

Interpreting Earth system conditions is central to understanding environmental risks and informing decisions across weather- and climate-sensitive sectors. Existing multimodal weather systems primarily target task-specific prediction, generation, or question answering, while general-purpose alignment between Earth system data and language remains underexplored due to the limited availability of diverse language supervision grounded in meteorological conditions. To fill this gap, we introduce EarthAlign, a large-scale dataset with broad geographic coverage spanning 2000-2024 that combines 10 expert-curated natural event and disaster data sources with climatology-derived normal-weather samples. Each sample includes temporal and geospatial information and four grounded caption styles aligned with 63-variable ERA5 meteorological data. Building on EarthAlign, we introduce MeteoLIP, a dual-encoder framework for learning aligned meteorology-language representations. MeteoLIP incorporates MetTok, which uses a geolocation- and time-conditioned query to aggregate variable-specific patch embeddings into a compact sequence of meteorology tokens. To comprehensively assess Earth system multimodal representations, we introduce three downstream tasks: cross-modal retrieval, weather-condition classification, and physical variable estimation. Our experiments show that MeteoLIP improves upon the corresponding CLIP and SigLIP baselines across these tasks. Further analyses highlight the importance of meteorological input, temporal and geospatial conditioning, and multi-style supervision for meteorology-language alignment. Thus, EarthAlign and MeteoLIP provide a foundation for learning and evaluating language-aligned representations of Earth system data. Our code, dataset, and weights are publicly available at https://github.com/mbzuai-oryx/EarthAlign.