中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 成都山地灾害与环境研究所
  3. 中国科学院水利部成都山地灾害与环境研究所
  4. 数字山地与遥感应用中心
Parcel-Level Mapping of Artificial Forests Along the Middle Reach Valley of Yarlung Tsangpo River Based on Deep Learning Algorithms

文献类型：期刊论文

作者Xia, Changshuo3,4; Zhao, Wei4; Tan, Jianbo3; Wu, Tianjun2; Ding, Tao1,4
刊名IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
出版日期2025
卷号22页码:5
关键词Forests Accuracy Feature extraction Image segmentation Training Rivers Deep learning Remote sensing Level set Data mining Artificial forests (AFs) deep learning (DL) image segmentation Yarlung Tsangpo River
ISSN号1545-598X
DOI10.1109/LGRS.2025.3543344
通讯作者Zhao, Wei(zhaow@imde.ac.cn)
英文摘要Artificial forest (AF) is an effective means of human intervention in forest ecosystems, aiming at preventing issues, such as soil erosion and land desertification. However, owing to the characteristics of large-scale afforestation projects, which often involve vast spatial extents and extended temporal scales, AF usually exhibits complex distribution patterns. In such cases, traditional remote sensing methods usually fail to accurately monitor AF conditions. To address this issue, this study introduced deep learning (DL) algorithms to extract multilevel features from remote sensing images for AF mapping and employed image processing techniques to enhance AF boundary determination. Through integrating these two approaches, high-resolution mapping of AF parcels was generated for a typical region in the middle reach valley of the Yarlung Tsangpo River. In the validation phase, the extracted regions were compared with manually labeled datasets and three accuracy metrics were calculated to demonstrate the extraction performance of the model. The accuracy reached 90.12% with the intersection over union (IoU) of 88.42%, and the cross-entropy loss function is only 0.0218. Meanwhile, three sampling areas with different coverages were selected for comparison, and the extractions have better performance than the SAM model based on the comparison with the samples. The findings reveal that this method can segment each AF parcel into independent objects, and the results would be helpful for parcel-based researches.
资助项目National Natural Science Foundation of China[42222109] ; Science and Technology Program of the Tibet Autonomous Region[XZ202401ZY0060] ; Science and Technology Research Program of Institute of Mountain Hazards and Environment, Chinese Academy of Sciences[IMHE-CXTD-02]
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001438183600017
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Science and Technology Program of the Tibet Autonomous Region ; Science and Technology Research Program of Institute of Mountain Hazards and Environment, Chinese Academy of Sciences
源URL[http://ir.imde.ac.cn/handle/131551/58771]  
专题成都山地灾害与环境研究所_数字山地与遥感应用中心
通讯作者Zhao, Wei
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Changan Univ, Sch Land Engn, Xian 710064, Peoples R China
3.Changsha Univ Sci & Technol, Coll Transportat Engn, Changsha 410114, Peoples R China
4.Chinese Acad Sci, Inst Mt Hazards & Environm, Chengdu 610299, Peoples R China
推荐引用方式
GB/T 7714		 Xia, Changshuo,Zhao, Wei,Tan, Jianbo,et al. Parcel-Level Mapping of Artificial Forests Along the Middle Reach Valley of Yarlung Tsangpo River Based on Deep Learning Algorithms[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2025,22:5.
APA Xia, Changshuo,Zhao, Wei,Tan, Jianbo,Wu, Tianjun,&Ding, Tao.(2025).Parcel-Level Mapping of Artificial Forests Along the Middle Reach Valley of Yarlung Tsangpo River Based on Deep Learning Algorithms.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,22,5.
MLA Xia, Changshuo,et al."Parcel-Level Mapping of Artificial Forests Along the Middle Reach Valley of Yarlung Tsangpo River Based on Deep Learning Algorithms".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 22(2025):5.

入库方式： OAI收割

来源：成都山地灾害与环境研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。