npj Climate and Atmospheric Science· 2026Q1
Generative assimilation and prediction for weather and climate
- 13citations
- Q1SCImago
- 2026year
Short summary
A new deep generative framework, GAP, unifies data assimilation and prediction for weather and climate, outperforming current methods in accuracy and stability for tasks from daily forecasts to millennial simulations.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces Generative Assimilation and Prediction (GAP), a unified deep generative framework for weather and climate.
- GAP integrates data assimilation with prediction, addressing limitations of current ML models.
- The framework quantifies probabilistic distributions of atmospheric states under observational and forcing constraints.
- GAP achieves competitive results in data assimilation, probabilistic weather forecasts, and seasonal predictions.
- GAP produces stable millennial simulations and reproduces climate variability from daily to decadal scales.
AI-generated from the title and abstract; the full text is not read.
Abstract
Machine learning models have shown great success in predicting weather up to two weeks ahead, outperforming process-based benchmarks. However, existing approaches mostly focus on the prediction task, and do not incorporate the necessary data assimilation. Moreover, these models suffer from error accumulation in long roll-outs, limiting their applicability to seasonal predictions or climate projections. Here, we introduce Generative Assimilation and Prediction (GAP), a unified deep generative framework for assimilation and prediction of both weather and climate. By learning to quantify the probabilistic distribution of atmospheric states under observational, predictive, and external forcing constraints, GAP excels in a broad range of weather-climate related tasks, including data assimilation, seamless prediction, and climate simulation. In particular, GAP is competitive with state-of-the-art ensemble assimilation, probabilistic weather forecast and seasonal prediction, yields stable millennial simulations, and reproduces climate variability from daily to decadal time scales.
The authors' abstract, as published at the source. npj Climate and Atmospheric Science, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Atmospheric Science
Atmospheric ScienceEarth and Planetary Sciences