# WeatherNext 3: Increasing resolution and performance of global weather models with raw observations

arXiv: https://arxiv.org/abs/2609.03582 · HTML: https://mlsanity.com/paper/2609.03582/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [MetNet: A Neural Weather Model for Precipitation Forecasting](https://mlsanity.com/paper/2003.12140/) (2020)
- [Deep Learning for Day Forecasts from Sparse Observations](https://mlsanity.com/paper/2306.06079/) (2023)
- [Skillful joint probabilistic weather forecasting from marginals](https://mlsanity.com/paper/2506.10772/) (2025)
- [Graph Element Networks: adaptive, structured computation and memory](https://mlsanity.com/paper/1904.09019/) (2019)
- [Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting](https://mlsanity.com/paper/2601.18111/) (2026)
- [U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster](https://mlsanity.com/paper/2604.09041/) (2026)
- [OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations](https://mlsanity.com/paper/2412.18239/) (2024)
- [A multi-scale loss formulation for learning a probabilistic model with proper score optimisation](https://mlsanity.com/paper/2506.10868/) (2025)
- [An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting](https://mlsanity.com/paper/2510.13050/) (2025)
- [Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction](https://mlsanity.com/paper/2508.18486/) (2025)
- [Skillful high-resolution weather forecasting independent of physical models](https://mlsanity.com/paper/2605.28153/) (2026)
- [Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting](https://mlsanity.com/paper/2606.26421/) (2026)

## Built on by (most cited first, 2 of 2)

- [Global Evaluation of AI and NWP Precipitation Forecasts During Atmospheric River Events](https://mlsanity.com/paper/2610.03758/) (2026)
- [Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation](https://mlsanity.com/paper/2610.15750/) (2026)

## Abstract (arXiv)

State-of-the-art AI weather models have shown impressive medium-range forecast skill and computational efficiency, but suffer two key shortcomings: their forecasts have lower spatial and temporal resolution than the best physics-based models and they are exclusively initialized with and trained on analysis data. As a result, they cannot directly make use of observations, and any biases in the analysis are inherited by the forecast. WeatherNext 3 addresses these shortcomings and establishes a new state-of-the-art for probabilistic medium-range forecasting skill. First, WeatherNext 3 generates new forecasts every hour (rather than every 6 hours like traditional global models) by ingesting low-latency geostationary satellite data. Second, WeatherNext 3's temporal and spatial resolution are on par with physics-based global models, with hourly time steps and 0.1 degree resolution for single-level variables, including solar radiation and cloud cover. Third, WeatherNext 3 moves beyond traditional analysis variables by learning to predict satellite-derived precipitation estimates, as well as tropical cyclone and station observations. Modelling sparse station data allows WeatherNext 3 to make 2m temperature and dewpoint predictions at any location and time, conditioned on local geographical features, with substantially lower error than competing global models, even when evaluated against unseen stations. Together, WeatherNext 3's capabilities move operational AI-based weather forecasting beyond emulating the traditionally distinct stages of data assimilation, forecasting and post-processing, which helps to further push the frontier of performance and granularity for global weather prediction.