Spatiotemporal patch identification and multiscale drivers of nonagricultural conversion of cultivated land in the Jianghan Plain

Abstract

Abstract The nonagricultural conversion of cultivated land (NACCL) poses a major challenge to cultivated land protection and food security in intensive agricultural regions. However, the reliable identification of NACCL in complex agricultural plains remains difficult because cultivated land, aquaculture ponds, shrimp–rice fields, greenhouses, water bodies, and rural settlements are often spatially interlaced and spectrally confused. Taking the Jianghan Plain, a major grain-producing region in central China, as the study area, this study used Sentinel-2 time-series imagery, percentile-based temporal metrics, spectral indices, and random forest classification on the Google Earth Engine platform to generate annual landuse maps from 2017 to 2021. The classification results achieved overall accuracies of 86%–92%, with Kappa coefficients of 0.77–0.87, and the producer’s accuracy of cultivated land reached 96.23%–100%. Compared with the ESRI 10 m land-use product, the classification results provided finer spatial details for cultivated land boundaries, indicating the reliability and applicability of the remote sensing interpretation method in complex agricultural plains. Based on the classification results, this study further diagnosed NACCL by combining landuse transition analysis, grid-based nonagricultural conversion rate measurement, and patch-scale cultivated-land overlay. It’s shown that patch-scale diagnosis could distinguish unchanged, changed, and suspected changed patches, thereby revealing both confirmed conversion and uncertainty caused by mixed land-use signals. Finally, multiscale geographically weighted regression (MGWR) was used to explain the spatial differentiation of NACCL. The results showed that NACCL was spatially heterogeneous and scale-dependent: natural factors exerted relatively broad and stable constraints, accessibility factors influenced conversion around transport corridors and urban fringes, and socioeconomic factors showed stronger local variation. This study provides a reliable remote sensing interpretation method, a patch-scale diagnostic perspective, and multiscale driving evidence for refined cultivated-land protection and high-risk area monitoring.