A near-real-time and unsupervised framework for grain crop harvest detection using sentinel-2 imagery: the reaped index (RI) and automated thresholding

Monitoring grain harvest events is crucial for crop management, yield estimation, and food security. Timely detection supports machinery allocation and mitigates risks from extreme weather. However, most existing studies rely on dense time series or labeled data, limiting real-time applications. This study proposes an unsupervised, index-based thresholding framework using Sentinel-2 imagery for major grain crops (paddy rice, maize, and wheat). A new Reaped Index (RI) was developed to distinguish harvested from unharvested fields based on their spectral differences. An adaptive thresholding algorithm addresses class imbalance across the early and late harvest stages. The framework was validated in Wuchang and Huaxian (China) and central Iowa (US), achieving F1 scores of 85–98 %, outperforming existing unsupervised approaches and vegetation indices. Therefore, this is a novel method for near-real-time harvest event detection, enabling label-free, rapid, and large-scale monitoring to support agricultural management under increasing weather risks.