An attention-enhanced spatial–temporal high-resolution network for irrigated area mapping using multitemporal Sentinel-2 images

作者：Wei Li, Qinchuan Xin, Ying Sun, Ying Sun, Yanqing Zhou, Jiangyue Li, Yidan Wang, Yu Sun, Yu Sun, Guangyu Wang, Ren Xu, Lu Gong, Yaoming Li · 发表于：International Journal of Applied Earth Observation and Geoinformation · 年份：2024 · DOI：10.1016/j.jag.2024.104040 · 被引用次数：7 · 研究领域：Remote Sensing in Agriculture、Smart Agriculture and AI、Advanced Image Fusion Techniques

• A novel deep leaning model using multitemporal remotely sensed imagery for irrigation extraction, named as the attention-enhanced spatial–temporal high-resolution network (AEST-HRNet). • A dataset containing 3031 samples for extracting irrigated farmland. • Our irrigation Map agree well with statistics from the United States National Agricultural Statistics Survey (NASS). • Our irrigation map outperforms publicly released maps. • Our method outperforms pixel-based classification using the random forest model and the convolution-based semantic segmentation methods. Accurate mapping of irrigated croplands is crucial for a comprehensive understanding of agricultural practices and land management. Despite recent advancements, there remains room for further exploration of the effective fusion of temporal information from multitemporal remote sensing images, which is essential for capturing the dynamic nature of agricultural landscapes. Many existing irrigation mapping methods concatenate multitemporal images in a direct way and thus neglect the temporal relationships within the image time series, especially the sequence and interdependencies of the temporal dimension. To address this gap, a novel deep learning model, named the attention-enhanced spatial–temporal high-resolution network (AEST-HRNet), which incorporates parallel processing and a fusion mechanism of multiresolution information streams, three-dimensional (3D) spatial–temporal convolution, and temporal attention modu...