WorldTensor: Harmonized Dataset for Earth System AI Models

Carlos Rodriguez-Pardo, Massimo Tavoni· July 7, 2026 View original

Key takeaways

  • WorldTensor is a new harmonized global dataset for Earth system foundation models.
  • It integrates diverse environmental and socioeconomic data onto a common grid.
  • The dataset addresses the need for unified training resources for multimodal AI.
  • It enables more holistic understanding of coupled Earth and human system dynamics.

Who benefits

Environmental ConsultingGovernmentInsuranceUrban PlanningEnergy

Summary

WorldTensor is a new harmonized global dataset that integrates hundreds of environmental and socioeconomic variables onto a standardized 0.25-degree spatial grid and annual temporal framework. It aims to address the lack of a unified training resource for multimodal Earth system foundation models, combining climate, land, ocean, infrastructure, and socioeconomic data.

Developing comprehensive Earth system foundation models has been hampered by the lack of a unified dataset that combines diverse environmental and human system data. Existing models primarily rely on physical climate and weather data, often neglecting the socioeconomic factors that influence and are affected by environmental change. To bridge this gap, WorldTensor has been introduced as a harmonized global dataset. It standardizes hundreds of variables, including climate, land use, oceanography, infrastructure, hazards, and socioeconomic indicators, onto a common 0.25-degree spatial grid and annual temporal framework. This resource was created by carefully re-gridding heterogeneous inputs, rasterizing point and vector data, and reconciling varying temporal coverages, providing a consistent foundation for training advanced multimodal Earth system AI.

Why it matters

This dataset is crucial for advancing Earth system modeling by enabling the development of more holistic AI models that can understand the complex interplay between environmental and human systems, leading to better predictions and policy decisions.

How to implement this in your domain

  1. 1Access and explore the WorldTensor dataset for potential applications in environmental impact assessment or climate risk analysis.
  2. 2Integrate WorldTensor into existing data science workflows to enrich analyses with a broader range of environmental and socioeconomic factors.
  3. 3Develop or fine-tune machine learning models using WorldTensor to predict coupled dynamics across Earth and human systems.
  4. 4Collaborate with research institutions to contribute to or leverage the ongoing development of Earth system foundation models.

Original post by Carlos Rodriguez-Pardo, Massimo Tavoni

"arXiv:2607.03298v1 Announce Type: new Abstract: Foundation models for Earth systems have so far been trained primarily on physical climate and weather data, with limited representation of the human systems that both drive and respond to environmental change. The lack of a unified…"

View on X

Originally posted by Carlos Rodriguez-Pardo, Massimo Tavoni on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research

AI ResearchAI Engineering & DevTools

Decoding Silent Reading from Non-Invasive EEG

This research demonstrates that open-vocabulary word-level and semantic information can be reliably decoded from non-invasive EEG during silent reading. Using a contrastive decoder and a large dataset from a single participant, the study shows decoding scales log-linearly with training data and extends to rare words.

Ingo Marquardt, Anthilia Alchanat, Priyanka JainAug 21, 2026
AI ResearchAI Engineering & DevTools

Exact Learning Coefficients for Singular Models

This paper presents the first deterministic algorithm for exactly computing local learning coefficients (Real Log Canonical Thresholds) for two-dimensional singular models. This breakthrough provides ground truth for calibrating sampling-based estimators and reveals algebraic structure in learning coefficients, outperforming sampling in shallow regimes.

Gr\'egoire Sergeant-Perthuis (CQSB, Sorbonne Universit\'e), Elias Tsigaridas (Ouragan Team, INRIA), Jules Tsukahara (Ouragan Team, INRIA)Aug 21, 2026
AI Engineering & DevToolsAI Research

Standardized ML Evaluation for Power System Protection

This paper proposes a standardized framework for evaluating machine learning applications in power system protection, addressing inconsistencies in current research. It defines seven critical study dimensions and instantiates the framework with a case study on fault classification and localization using a public benchmark.

Julian Oelhaf, Georg Kordowich, Paula Andrea P\'erez-Toro, Christian Bergler, Johann J\"ager, Andreas Maier, Siming BayerAug 21, 2026