Bridging the weather and climate divide with artificial intelligence

Преодоление разрыва между метеорологией и климатологией с помощью искусственного интеллекта
Gustau Camps‐Valls, Alberto Carrassi, Francisco de Melo Viríssimo, Kevin Debeire, Miguel‐Ángel Fernández‐Torres, Philipp Hess, Helge Heuer, Nathan Mankovich, David Montero, Esther Rodrigo Bonet, Federico Serva, Vasileios Sitokonstantinou, Alistair White, Kai-Hendrik Cohrs, Jonathan Wider, Christian Reimers, Nikolaos Ioannis Bountos, Ioannis Papoutsis, Pierre Gentine, Veronika Eyring
2026-08-18

Earth observationsartificial intelligenceclimate predictionunified Earth-system modelsweather forecasting
Weather and climate shape every aspect of our lives, yet for decades they have been studied as separate worlds—one concerned with what happens tomorrow, the other with what awaits us over the coming decades. This long-standing divide has slowed progress in both fields. Here, we argue that artificial intelligence (AI) is helping to dissolve the boundary between them. By learning directly from vast streams of Earth observations, AI is starting to predict both tomorrow’s storm and next century’s climate within a single, unified framework. We show how this convergence is already underway, why weather and climate science have much to gain from each other, and what still stands in the way—from trust, transparency, and fairness to the energy cost of computation and the risk of widening global inequalities. Realizing this vision will demand not only better algorithms but a new culture of collaboration across scientific communities, operational centers, fields and disciplines. Done well, a unified, AI-driven Earth science could deliver faster, more reliable, and more actionable predictions—helping societies anticipate and adapt to a rapidly warming planet. Weather forecasting and climate prediction have long developed in isolation. This Perspective argues that artificial intelligence is dissolving that divide, enabling unified Earth-system models that span from tomorrow’s storms to the climate of coming decades.
1
Achieving unified AI-driven Earth science requires stronger collaboration across scientific communities, operational centers, fields, and disciplines.
2
Artificial intelligence is beginning to unify weather forecasting and climate prediction within shared Earth-system modeling frameworks.
3
Closer integration between weather and climate science could accelerate progress and produce faster, more reliable, and more actionable predictions.
4
Learning directly from large streams of Earth observations enables AI systems to address prediction timescales ranging from tomorrow’s storms to coming decades.
5
Major barriers include insufficient trust and transparency, fairness concerns, high computational energy costs, and risks of widening global inequalities.

AI-driven unified Earth-system models spanning weather forecasting and climate prediction

The convergence of weather forecasting and climate prediction, including the capabilities, benefits, and challenges of unified AI-based prediction

Publication Details
Publication Date
2026-08-18
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Gustau Camps‐Valls
Alberto Carrassi
Francisco de Melo Viríssimo
Kevin Debeire
Miguel‐Ángel Fernández‐Torres
Philipp Hess
Helge Heuer
Nathan Mankovich
David Montero
Esther Rodrigo Bonet
Federico Serva
Vasileios Sitokonstantinou
Alistair White
Kai-Hendrik Cohrs
Jonathan Wider
Christian Reimers
Nikolaos Ioannis Bountos
Ioannis Papoutsis
Pierre Gentine
Veronika Eyring
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%