基于深度学习的四川盆地丘陵区县域耕地遥感识别研究  

Remote Sensing Identification Method of Cultivated Land at Hill County of Sichuan Basin Based on Deep Learning

作　　者：李豪 杜雨秋 肖星竹 陈彦羲 LI Hao;DU Yuqiu;XIAO Xingzhu;CHEN Yanxi(College of Resources,Sichuan Agricultural University,Chengdu 611130,China;Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China;University of Chinese Academy of Sciences,Beijing 101408,China)

机构地区：[1]四川农业大学资源学院,四川成都611130 [2]中国科学院地理科学与资源研究所,北京100101 [3]中国科学院大学,北京101408

出　　处：《智慧农业（中英文）》2024年第3期34-45,共12页Smart Agriculture

基　　金：国家自然科学基金项目(41501291);国家级大学生创新训练计划项目(202110626010);四川天府新区乡村振兴研究院“揭榜挂帅”项目(XZY1-14)。

摘　　要：[目的/意义]耕地识别是农业遥感的重要应用领域之一,但现阶段深度学习等人工智能方法在中国西南丘陵区遥感识别的研究应用深度仍然不够,识别精度有待提升。[方法]为了快速、精确地获取耕地面积、分布等信息,基于高分辨率的高分六号(GF-6)遥感影像,运用UNet++、DeeplabV3+、UNet与PSPNet等新型深度学习模型对四川省绵阳市三台县耕地信息进行识别,并对各深度学习模型、传统机器学习方法——随机森林法及新型土地覆盖产品SinoLC-1的识别精度进行对比分析,以期深入探索深度学习方法在地物遥感识别领域的应用前景。[结果和讨论]深度学习模型在F_(1)分数、整体精度(Overall Accuracy,OA)、Kappa系数等精度评价指标的表现上,相比于传统机器学习方法和新型土地覆盖产品均有显著提升,精度提升幅度分别可达20%和50%;其中添加了密集跳跃连接技术的UNet++模型的识别效果最好,其F_(1)分数、交并比(Intersection over Union,IoU)、平均交并比(Mean Intersection over Union,MIoU)、OA值和Kappa系数值分别为0.92、85.93%、81.93%、90.60%和0.80。应用UNet++模型对2种由仅光谱特征以及光谱+地形特征两种不同特征构建的影像进行耕地提取,光谱+地形特征模型的IoU、OA和Kappa 3个指标比仅光谱特征模型分别提高了0.98%、1.10%和0.01。[结论]深度学习技术在应用于高分辨率遥感影像中的耕地识别方面展现出显著的实用价值,融合光谱和地形特征可以实现信息互补,能进一步改善耕地的识别效果。本研究可为相关部门更好地管理和利用耕地资源、推动农业可持续发展提供技术支撑。[Objective]To fully utilize and protect farmland and lay a solid foundation for the sustainable use of land,it is particularly important to obtain real-time and precise information regarding farmland area,distribution,and other factors.Leveraging remote sensing technology to obtain farmland data can meet the requirements of large-scale coverage and timeliness.However,the current research and application of deep learning methods in remote sensing for cultivated land identification still requires further improvement in terms of depth and accuracy.The objective of this study is to investigate the potential application of deep learning methods in remote sensing for identifying cultivated land in the hilly areas of Southwest China,to provide insights for enhancing agricultural land utilization and regulation,and for harmonizing the relationship between cultivated land and the economy and ecology.[Methods]Santai county,Mianyang city,Sichuan province,China(30°42'34"~31°26'35"N,104°43'04"~105°18'13"E)was selected as the study area.High-resolution imagery from two scenes captured by the Gaofen-6(GF-6)satellite served as the primary image data source.Additionally,30-meter resolution DEM data from the United States National Aeronautics and Space Administration(NASA)in 2020 was utilized.A land cover data product,SinoLC-1,was also incorporated for comparative evaluation of the accuracy of various extraction methods'results.Four deep learning models,namely Unet,PSPNet,DeeplabV3+,and Unet++,were utilized for remote sensing land identification research in cultivated areas.The study also involved analyzing the identification accuracy of cultivated land in high-resolution satellite images by combining the results of the random forest(RF)algorithm along with the deep learning models.A validation dataset was constructed by randomly generating 1000 vector validation points within the research area.Concurrently,Google Earth satellite images with a resolution of 0.3 m were used for manual visual interpretation to determine the land

关 键 词：深度学习 遥感影像 耕地识别 精度评价 丘陵地区 

分 类 号：P237[天文地球—摄影测量与遥感]