评估GraphCast人工智能对印度夏季风预测的保真度：基于ERA-5再分析和IMERG观测的气候学评估
GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG
浏览论文内容
中文总结 AI 辅助
该研究评估GraphCast对印度夏季风预测的保真度，将其与ERA5再分析和IMERG观测对比，分析不同提前期性能，发现GraphCast在短提前期能再现季风降雨模式，但存在湿偏差、降雨方差抑制等问题，为下一代AI天气模型提供关键诊断。
中文摘要 AI 辅助
印度夏季风是全球气候系统中最重要且动态复杂的现象之一，其预测对基于物理和数据驱动的模型都具有挑战性。本研究在2021 - 2024年北半球夏季（6 - 9月）期间，将谷歌的基于机器学习的全球天气预报系统GraphCast与ERA5再分析和IMERG降水观测进行对比。分析了00 UTC初始化的确定性GraphCast预测，使用四个6小时提前期，在印度夏季风区域对 +24 h、+48 h和 +72 h提前期性能进行合成。评估包括气候平均状态、降雨强度分布、热力驱动因素、季风动力学以及多个时间尺度上的变率。结果表明，GraphCast在短提前期能较好地再现季风降雨的广泛空间模式和年循环，但在核心季风区域存在平均湿偏差，且几乎在所有时间尺度上对降雨方差有强烈抑制。降雨强度分布右移且压缩，中到大雨（第95百分位数）偏湿，极端事件代表性不足。这些偏差伴随着低层对流层Q1剖面不足和向北传播的季节内变率退化。总体而言，GraphCast在降水中显示出确定性平滑特征，为下一代人工智能天气模型及其在热带延伸期预报中的应用提供了关键诊断。
英文摘要
The Indian Summer Monsoon (ISM) is one of the most dynamically complex components of the global climate system, yet its accurate prediction remains challenging for both physics-based and emerging AI weather models. We present a climatological evaluation of Google's GraphCast against ERA5 reanalysis and the Integrated Multi-satellitE Retrievals for GPM (IMERG) precipitation dataset during the boreal summer (June-September, JJAS) for 2021-2024. Deterministic GraphCast forecasts initialized at 00 UTC are composited to evaluate +24 h, +48 h, and +72 h lead times over the full ISM domain. The analysis examines the climatological mean state (rainfall, surface temperature, and low-level winds), rainfall intensity distribution, thermodynamic structure (tropospheric temperature gradient, DTT; apparent heat source and moisture sink, Q1 and Q2), monsoon dynamics (vertical wind shear), and rainfall variability across intraseasonal, synoptic, and spectral timescales. GraphCast reproduces the broad spatial pattern and seasonal evolution of monsoon rainfall with good fidelity at short lead times but exhibits a domain-averaged wet bias over the core monsoon region. It also substantially suppresses rainfall variability across nearly all timescales (regional power-spectrum variance ratio of 0.14 relative to IMERG) and produces a compressed rainfall intensity distribution, overestimating moderately heavy rainfall (95th percentile) while systematically underrepresenting the most extreme events. These biases are accompanied by a deficient lower-tropospheric Q1 profile and weaker northward-propagating intraseasonal variability. Together, the results reveal a consistent deterministic-smoothing signature in GraphCast's precipitation forecasts and provide benchmark diagnostics for evaluating next-generation AI weather models for tropical medium-range forecasting (+24 h to +72 h).
