基于深度学习的遥感影像时空融合及冬小麦种植面积提取  

Spatiotemporal Fusion of Remote Sensing Images based on Deep Learning and Extraction of Winter Wheat Planting Area

作　　者：张娟娟[1,2] 谢一敏 董萍 孟圣博 司海平 王晓平[4] 马新明 ZHANG Jüanjüan;XIE Yimin;DONG Ping;MENG Shengbo;SI Haiping;WANG Xiaoping;MA Xinming(Henan Agricultural University,Science College of Information and Management,Zhengzhou 450002,China;Henan Agricultural University,Collaborative Innovation Center of Henan Grain Crops,Zhengzhou 450002,China;College of Agronomy,Henan Agricultural University,Zhengzhou 450002,China;Henan Province Jindun Seed Industry Company Limited,Luohe 462003,China)

机构地区：[1]河南农业大学信息与管理科学学院,河南郑州450002 [2]河南粮食作物协同创新中心,河南郑州450002 [3]河南农业大学农学院,河南郑州450002 [4]河南省金囤种业有限公司,河南漯河462003

出　　处：《遥感技术与应用》2023年第3期578-587,共10页Remote Sensing Technology and Application

基　　金：国家重点研发计划项目(2021YFD1700905);河南省科技攻关项目(192102110012);河南省现代农业(小麦)产业技术体系项目(S2016-01-G04)。

摘　　要：利用遥感技术快速、准确地进行冬小麦种植面积提取对农作物估产和粮食安全具有重要意义。由于中高分辨率时序影像受重访周期、云雨天气等影响难以获取,而低分辨率遥感数据在作物种植信息提取上精度低等问题,以河南省长葛市为例,获取2015~2020年间的Landsat 8和MODIS影像为数据集,基于优化后的卷积神经网络时空融合模型对2种数据进行融合,构建30 m分辨率的NDVI时间序列集,采用S-G(Savitzky-Golay)滤波对时序集进行去噪,最后利用随机森林方法对冬小麦种植面积进行提取。结果表明:优化后的融合模型鲁棒性较好,预测影像与真实影像R^(2)均在0.92以上。研究区小麦面积提取与统计面积的一致性为97.3%,结果可靠。因此,优化后的模型能较好地融合出中高分辨率影像,是一种有效的补充缺失影像的技术手段,构建的时序集能较为准确地提取县域小麦种植面积。Rapid and accurate winter wheat acreage extraction using remote sensing technology is of great impor⁃tance for crop yield estimation and food security.Due to problems such as the difficulty of obtaining medium and high resolution time-series images due to revisit cycles,cloud and rain,and the low accuracy of low resolution remote sensing data in extracting crop planting information.In this study,taking Changge City,Henan Prov⁃ince as an example,Landsat 8 and MODIS images were obtained as the dataset during 2015~2020,and the 2 data were fused based on an optimized convolutional neural network spatio-temporal fusion model to construct a 30 m resolution NDVI time series set,and S-G(Savitzky-Golay)filtering was used to denoise the time se⁃ries set,and finally The area planted with winter wheat was extracted using the RF method.The results show that the optimised fusion model is robust and the R^(2) of both the predicted and real images is above 0.92.The agreement between wheat area extraction and statistical area in the study area was 97.3%and the results were reliable.Therefore,the optimised model can better fuse the medium and high resolution images,which is an ef⁃fective technical means to supplement the missing images,and the constructed time series set can more accurate⁃ly extract the wheat planting area in the county.

关 键 词：多源遥感 时空融合 卷积神经网络 分类 种植面积 

分 类 号：S127[农业科学—农业基础科学] TP75[自动化与计算机技术—检测技术与自动化装置]