Mapping irrigated, rainfed and paddy croplands from time-series Sentinel-2 images by integrating pixel-based classification and image segmentation on Google Earth Engine

Abstract

Accurate distribution of irrigated, rainfed and paddy croplands is essential for food production and agricultural management. High spatial resolution land cover datasets rarely have detailed information about irrigated or rainfed croplands, while cropland datasets labelled with crop watering methods face challenges with coarse temporal and spatial resolution. This study proposed a semi-automatic detailed croplands mapping framework by integrating pixel-based classification and image segmentation. First, high-quality Sentinel-2 images were selected and mosaicked to time-series image dataset using Google Earth Engine platform. Second, pixel-based random forest classification and the Simple Non-Iterative Clustering image segmentation were integrated by optimal rules for generating 10-m resolution Detailed Croplands Map (DCM-2020). The DCM-2020 was assessed by using validation samples, and the overall accuracy of the map was 88.6% with kappa coefficient of 0.83. Compared with the existing cropland datasets, DCM-2020 shows much finer details, and croplands area is closer to official statistics.