文献类型： 外文期刊

作者： Liu, Tianjiao ¹ ; Duan, Si-Bo ¹ ; Liu, Niantang ¹ ; Zhang, Youzhi ² ; Chen, Jiankui ³ ; Zhang, Li ⁴ ; Li, Dong ⁵ ;

作者机构： 1.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, State Key Lab Efficient Utilizat Arable Land China, Beijing 100081, Peoples R China

2.Inst Agr Remote Sensing & Informat, Heilongjiang Acad Agr Sci, Harbin 150086, Peoples R China

3.Hebei Oriental Univ, Sch Artificial Intelligence, Langfang 065001, Peoples R China

4.Guizhou Univ, Coll Big Data & Informat Engn, Guiyang 550025, Peoples R China

5.Chinese Acad Sci, Yantai Inst Coastal Zone Res, Yantai 264003, Peoples R China

关键词： Feature extraction; Crops; Accuracy; Remote sensing; Transformers; Data mining; Training; Long short term memory; Data models; Vegetation mapping; Active learning; hybrid deep learning model; rice extraction; Sentinel-2 spectral-temporal-spatial imagery

期刊名称：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING （ 影响因子：8.6； 五年影响因子：8.8 ）

ISSN： 0196-2892

年卷期： 2025 年 63 卷

页码：

收录情况： SCI

摘要： Rice extraction in complex landscapes is a challenging issue in remote sensing, particularly in areas with diverse land-use types and spatiotemporal variability. To enhance the accuracy of rice extraction, this study proposes a novel approach integrating Sentinel-2 spectral-temporal-spatial imagery with a hybrid deep learning architecture for extracting single-cropping and double-cropping rice. First, a time-series dataset of spectral and texture features was constructed to capture the seasonal variations of rice. Second, an active learning strategy was employed to select high-confidence samples, and spectral, temporal, and spatial information was integrated into a unified dataset. Finally, a hybrid deep learning model, convolutional-Transformer hybrid network (CTH-Net), was developed, combining convolutional neural networks (CNNs) and Transformer networks. The model incorporates a fusion module to effectively integrate multiscale temporal, spatial, and spectral features and a residual module to improve gradient flow, mitigating the vanishing gradient problem in deep networks. Results demonstrate that the CTH-Net achieved 99.69% overall accuracy in rice extraction, maintaining >96% accuracy for single-cropping rice, double-cropping rice, and abandoned land. It outperformed models like CNNs, Transformers, long short-term memory (LSTM), and support vector machines (SVMs) in handling fragmented rice distributions and mixed land types, significantly improving extraction accuracy. This study provides an efficient and reliable solution for rice extraction in complex landscapes, supporting agricultural monitoring and management.