数字农科院2.0

A temporal-spatial deep learning network for winter wheat mapping using time-series Sentinel-2 imagery

文献类型： 外文期刊

作者： Lingling Fan;Lang Xia;Jing Yang;Xiao Sun;Shangrong Wu;Bingwen Qiu;Jin Chen;Wenbin Wu;Peng Yang

作者机构：

关键词： Deep learning;Sentinel-2;Temporal-spatial fusion;Time series;Wheat mapping

期刊名称： ISPRS Journal of Photogrammetry and Remote Sensing

ISSN： 0924-2716

年卷期： 2024 年 214 卷

页码：

收录情况： SCIE（2024版） ; ; EI（2024版）

摘要： Accurate mapping of winter wheat provides essential information for food security and ecosystem protection. Deep learning approaches have achieved promising crop discrimination performance based on multitemporal satellite imagery. However, due to the high dimensionality of the data, sequential relations, and complex semantic information in time-series imagery, effective methods that can automatically capture temporal-spatial features with high separability and generalizability have received less attention. In this study, we proposed a U-shaped CNN-Transformer hybrid framework based on an attention mechanism, named the U-Temporal-Spatial-Transformer network (UTS-Former), for winter wheat mapping using Sentinel-2 imagery. This model includes an “encoder-decoder” structure for multiscale information mining of time series images and a temporal-spatial transformer module (TST) for learning comprehensive temporal sequence features and spatial semantic information. The results obtained from two study areas indicated that our UTS-Former achieved the best accuracy, with a mean MCC of 0.928 and an F1-score of 0.950, and the results of different band combinations also showed better performance than other popular time-series methods. We found that the MCC (MCC/All) of the UTS-Former using only RGB bands decreased by 4.53 %, while it decreased by 13.36 % and 35.02 % for UNet2d-LSTM and CNN-BiLSTM, respectively, compared with that of all the band combinations. The comparison demonstrated that the proposed UTS-Former could capture more global temporal-spatial information from winter wheat fields and achieve greater precision in terms of local details than other methods, resulting in high-quality mapping. The analysis of attention scores for the available acquisition dates revealed significant contributions of both beginning and ending growth images in winter wheat mapping, which is valuable for making appropriate selections of image dates. These findings suggest that the proposed approach has great potential for accurate, cost-effective, and high-quality winter wheat mapping.

分类号：

  • 相关文献

[1]Cross-sensor data reconstruction for optical remote sensing gap-filling with attention-enhanced multi-scale fusion network. Xi Wang,Songchao Chen,Chang Zhou,Si Bo Duan,Zhou Shi. 2025

[2]基于时序Sentinel-2影像的梨树县作物种植结构. 刘俊伟,陈鹏飞,张东彦,赵红伟. 2020

[3]基于无人机与卫星遥感的草原地上生物量反演研究. 李淑贞,徐大伟,范凯凯,陈金强,佟旭泽,辛晓平,王旭. 2022

[4]基于多时相遥感植被指数的柑橘果园识别. 梁晨欣,黄启厅,王思,王聪,余强毅,吴文斌. 2021

[5]Sentinel-2宽波段光谱指数预测拔节后受冻冬小麦减产率. 赵爱萍,马浚诚,武永峰,胡新,任德超,李崇瑞. 2022

[6]东北三省2020-2022年间10 m空间分辨率耕地资源空间分布数据集. 申格,刘航,李丹丹,陈实,邹金秋. 2023

[7]多源中高分辨率影像协同下时间合成窗口对农作物识别的影响. 童婉婷,魏浩东,杨靖雅,金文捷,宋茜,胡琼,尹高飞,徐保东. 2024

[8]基于作物参考曲线法的冬小麦NDVI时间序列重建——以河北省部分区域为例. 敖洋钎,王永前,孙政,孙亮. 2025

[9]农田玉米秸秆覆盖类型的光学和微波遥感识别潜力分析. 张文茜,李文娟,余强毅,唐华俊,王聪,吴文斌. 2025

[10]Prediction For Hog Prices Based O.n Similar Sub-Series Search A nd Support Vector Regression. Wang, Dongjie,Liu, Yiran,Zhang, Zhentao,Liu, Chunhong,Duan, Qingling. 2019

[11]Declines in soil carbon storage under no tillage can be alleviated in the long run. Andong Cai,Tianfu Han,Tianjing Ren,Jonathan Sanderman,Yichao Rui,Bin Wang,Pete Smith,Minggang Xu,Yu'e Li. 2022

[12]Impacts of mining on vegetation phenology and sensitivity assessment of spectral vegetation indices to mining activities in arid/semi-arid areas. Xiaofei Sun,Yingzhi Zhou,Songsong Jia,Huaiyong Shao,Meng Liu,Shiqi Tao,Xiaoai Dai. 2024

[13]An improved change detection method for tacking remote sensing time series trends. Huo, Xing,Zhang, Kun,Li, Jing,Shao, Kun,Cui, Guangpeng. 2023

[14]Crop specific inversion of PROSAIL to retrieve green area index (GAI) from several decametric satellites using a Bayesian framework. Jingwen Wang,Raul Lopez-Lozano,Marie Weiss,Samuel Buis,Wenjuan Li,Shouyang Liu,Frédéric Baret,Jiahua Zhang. 2022

[15]Automated soybean mapping based on canopy water content and chlorophyll content using Sentinel-2 images. Huang, Yingze,Qiu, Bingwen,Chen, Chongcheng,Zhu, Xiaolin,Wu, Wenbin,Jiang, Fanchen,Lin, Duoduo,Peng, Yufeng. 2022

[16]Crop type mapping with temporal sample migration. Zhang, Shibo,Yang, Jingya,Leng, Pei,Ma, Yuman,Wang, Hongyang,Song, Qian. 2023

[17]Detection of Soil Erosion Hotspots in the Croplands of a Typical Black Soil Region in Northeast China: Insights from Sentinel-2 Multispectral Remote Sensing. Lulu Qi,Pu Shi,Klara Dvorakova,Kristof Van Oost,Qi Sun,Hanqing Yu,Bas van Wesemael. 2023

[18]Crop Mapping Based on Temporal and Spatial Sample Migrations: A Case Study Over Three Counties in Heilongjiang Province, Northeast China. Zuo, Hao-Nan,Leng, Pei,Li, Yu-Xuan,Song, Qian,Li, Zhao-Liang. 2024

[19]In-Season Crop Type Detection by Combing Sentinel-1A and Sentinel-2 Imagery Based on the CNN Model. Mao, Mingxiang,Zhao, Hongwei,Tang, Gula,Ren, Jianqiang. 2023

[20]Estimating Fraction of Absorbed Photosynthetically Active Radiation of Winter Wheat Based on Simulated Sentinel-2 Data under Different Varieties and Water Stress. Sun Z.,Sun L.,Liu Y.,Li Y.,Crusiol L.G.T.,Chen R.,Wuyun D.. 2024

作者其他论文 更多>>