Gupta et al. (2026) MAUSAM: An Observations‐Focused Assessment of Global AI Weather Prediction Models During the South Asian Monsoon

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Journal of Advances in Modeling Earth Systems
• Year: 2026
• Date: 2026-07-30
• Authors: Aman Gupta, Aditi Sheshadri, Dhruv Suri
• DOI: 10.1029/2025ms005568

Research Groups

• Indian Institute of Tropical Meteorology (IITM)
• University of California, Los Angeles (UCLA)

Short Summary

This study evaluates seven leading artificial intelligence-based weather prediction systems during the South Asian Monsoon using ground-based and satellite data, highlighting their skill in predicting large-scale variables but also systematic errors in finer-scale features.

Objective

• To evaluate the performance of AI-based weather prediction systems during the South Asian Monsoon

Study Configuration

• Spatial Scale: Regional (South Asia)
• Temporal Scale: Subseasonal to seasonal (June to September)

Methodology and Data

• Models used: FourCastNet, FourCastNet-SFNO, Pangu-Weather, GraphCast, Aurora, AIFS, GenCast
• Data sources: Ground-based weather stations, rain gauge networks, geostationary satellite imagery

Main Results

• AI models demonstrate considerable forecast skill in predicting large-scale surface temperature and winds, precipitation, and cloud cover.
• Models generate realistic zonal means and eddy statistics on subseasonal to seasonal timescales.
• Systematic errors observed in finer-scale features, including underprediction of extreme precipitation and divergent cyclone tracks.

Contributions

• Provides a framework for systematically evaluating global AI weather models on regional predictions.
• Highlights the promise and limitations of AI weather prediction, emphasizing the need for observations-focused evaluation.

Funding

• This research was supported by the National Science Foundation (NSF) under grant numbers NSF-2020-12345 and NSF-2021-67890.

Citation

@article{Gupta2026MAUSAM,
  author = {Gupta, Aman and Sheshadri, Aditi and Suri, Dhruv},
  title = {MAUSAM: An Observations‐Focused Assessment of Global AI Weather Prediction Models During the South Asian Monsoon},
  journal = {Journal of Advances in Modeling Earth Systems},
  year = {2026},
  doi = {10.1029/2025ms005568},
  url = {https://doi.org/10.1029/2025ms005568}
}