# How AI is changing weather forecasting

- Show: [Catalyst](https://hardwarepodcasts.com/podcast/catalyst)
- Published: 2026-01-02
- Length: 44m
- Page: https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting

## Summary

Peter Battaglia, senior director of research at Google DeepMind’s sustainability program, explains how AI models like transformers and graph neural networks are improving weather forecasting by capturing complex spatial dependencies that traditional numerical models miss. He details the shift from coarse global forecasts to high-resolution, application-specific predictions, highlighting the challenge of predicting precipitation and the potential of novel data sources like cell phones and social media. Battaglia discusses the historical context of government weather bureaus like NOAA and ECMWF, and outlines future applications in energy grid management, supply chain planning, and disaster response.

## Chapters

- [2:27](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=147) Introduction: The mechanism of AI in weather forecasting
- [4:26](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=266) History of weather forecasting: From government bureaus to post-processing
- [10:38](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=638) The physics of weather: Fluid dynamics, chaos, and the butterfly effect
- [14:53](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=893) Historical improvements: Data, compute, and model resolution
- [20:01](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=1201) The difficulty of predicting precipitation vs. temperature
- [23:10](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=1390) AI architectures: Transformers, graph neural networks, and supervised learning
- [28:52](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=1732) Spatial awareness: How AI treats hurricanes as macroscopic objects
- [36:30](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=2190) Data availability: ERA5, historical records, and novel data sources
- [42:02](https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting#t=2522) Future applications: Energy grids, supply chains, and crisis handling

## Topics

- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Energy & climate tech](https://hardwarepodcasts.com/topic/energy-and-climate-tech)
- [Sensors & measurement in products](https://hardwarepodcasts.com/topic/sensors)
- [Connected products & IoT](https://hardwarepodcasts.com/topic/connected-products-and-iot)

## Most relevant to

early-stage companies

## Mentioned

- Google DeepMind (company)
- NOAA (company)
- ECMWF (company)
- ERA5 (other)
- transformers (other)
- graph neural networks (other)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/catalyst/2026-01-02-how-ai-is-changing-weather-forecasting. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Catalyst.