GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG
Abstract
The Indian Summer Monsoon (ISM) is one of the most dynamically complex phenomena in the global climate system, yet its accurate prediction remains challenging for both physics-based and data-driven models. This study presents a systematic climatological evaluation of Google's GraphCast, a machine-learning global weather prediction system, against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024. We analyze deterministic GraphCast forecasts initialized at 00 UTC across 6-hourly steps to assess +24h, +48h, and +72h performance over the full ISM domain. The evaluation covers the climatological mean state (spatial rainfall, surface temperature, low-level winds), rainfall intensity distributions, thermodynamic drivers (tropospheric temperature gradient, DTT; apparent heat source and moisture sink, Q1 and Q2), monsoon dynamics (vertical wind shear, meridional structure), and variability across intraseasonal, synoptic, and spectral scales. GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, showing a near-zero domain-averaged rainfall bias over the core monsoon zone (-0.7 to -1.2 mm/day) and high daily temporal correlation with IMERG (0.89-0.92). However, temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile. GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. Overall, GraphCast shows a moderate underrepresentation of rainfall intensity and variance rather than a wet bias or variance collapse, providing benchmark diagnostics for AI weather models.
Related
- Physics vs. AI in weather prediction: evaluating GraphCast, AIFS, and FuXi against an observation-corrected WRF model for flash floods
- Can We Trust Evaluations of AI Weather Forecasts for Extremes? How Evaluation Protocols Shape Model Rankings
- Global Evaluation of AI and NWP Precipitation Forecasts During Atmospheric River Events
- A Multidimensional Evaluation Framework for Artificial Intelligence-Based Ocean State Forecasts
- Evaluating Neural Probabilistic Forecasts of Sparse Earthquake Counts: What Survives a Careful Evaluation
BibTeX
@misc{luitel2026graphcast,
title = {{GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG}},
author = {Somnath Luitel and Parthasarathi Mukhopadhyay and Manmeet Singh and Sandeep Juneja and Saptarishi Dhanuka},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.11905},
eprint = {2607.11905},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.11905},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG
AU - Somnath Luitel
AU - Parthasarathi Mukhopadhyay
AU - Manmeet Singh
AU - Sandeep Juneja
AU - Saptarishi Dhanuka
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2607.11905
UR - https://arxiv.org/abs/2607.11905
AB - The Indian Summer Monsoon (ISM) is one of the most dynamically complex phenomena in the global climate system, yet its accurate prediction remains challenging for both physics-based and data-driven models. This study presents a systematic climatological evaluation of Google's GraphCast, a machine-learning global weather prediction system, against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024. We analyze deterministic GraphCast forecasts initialized at 00 UTC across 6-hourly steps to assess +24h, +48h, and +72h performance over the full ISM domain. The evaluation covers the climatological mean state (spatial rainfall, surface temperature, low-level winds), rainfall intensity distributions, thermodynamic drivers (tropospheric temperature gradient, DTT; apparent heat source and moisture sink, Q1 and Q2), monsoon dynamics (vertical wind shear, meridional structure), and variability across intraseasonal, synoptic, and spectral scales. GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, showing a near-zero domain-averaged rainfall bias over the core monsoon zone (-0.7 to -1.2 mm/day) and high daily temporal correlation with IMERG (0.89-0.92). However, temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile. GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. Overall, GraphCast shows a moderate underrepresentation of rainfall intensity and variance rather than a wet bias or variance collapse, providing benchmark diagnostics for AI weather models.
ER -