AI4ESP logo
Artificial Intelligence for Earth System Predictability

A multi-lab initiative working with the Earth and Environmental Systems Science Division (EESSD) of the Office of Biological and Environmental Research (BER) to develop a new paradigm for Earth system predictability focused on enabling artificial intelligence across field, lab, modeling, and analysis activities.

AI4ESP Workshop Report

With gratitude to the over 740 participants from 178 institutions, the AI4ESP workshop report is available! From October - December 2021, participants discussed how Artificial Intelligence (AI) can enhance Earth system predictability across field, lab, modeling, and analysis activities. Results of this workshop are summarized in the executive summary, which accompanies a large full report with a workshop summary and section report for each session held.

Idealized Roadmap for Success

The illustration below shows a roadmap to the execution of AI4ESP encompassing near- (2-year), mid- (5-year), and long-term (10-year) activities (Source: Lawrence Berkeley National Laboratory)
Illustration showing a road with near term, mid term, and long term activities

Near Term (<2 years)

  • Open benchmark datasets
  • AI-enabled observations and data products based on gaps
  • Seed efforts to demonstrate potential of AI in existing programs and modeling frameworks
  • Cross-disciplinary collaborations to initiate activities

Mid Term (<5 years)

  • AI research centers
  • Measurable improvement in Earth system models with better representation of human activities
  • New AI techniques tailed for Earth science applications
  • Established interdisciplinary workforce
  • Open science culture with data sharing using standards, co-developed models

Long Term (<10 years)

  • Improved Earth system understanding and predictions
  • Supporting stakeholder needs and relevant scales for decision making


The AI4ESP initiative is a collaboration between DOE management and laboratories to understand the paradigm shift required to enable AI across the MODEX enterprise, in part by determining the most impactful applications along the observation-modeling continuum.