Show simple item record

Extraction of Cotton Cultivation Areas Based on Deep Learning and Sentinel-2 Image Data

dc.contributor.authorLiyuan Li
dc.contributor.authorHongfei Tao
dc.contributor.authorYan Xu
dc.contributor.authorLixiran Yu
dc.contributor.authorQiao Li
dc.contributor.authorHong Xie
dc.contributor.authorYouwei Jiang
dc.contributor.otherCollege of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China
dc.contributor.otherCollege of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China
dc.contributor.otherXinjiang Uygur Autonomous Region Ecological Water Resources Research Center, Academician and Expert Workstation of the Department of Water Resources of the Xinjiang Uygur Autonomous Region, Urumqi 830052, China
dc.contributor.otherCollege of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China
dc.contributor.otherCollege of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China
dc.contributor.otherChangji Water Conservancy Management Station, Santunhe River Basin Management Office, Changji 831100, China
dc.contributor.otherCollege of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China
dc.date.accessioned2025-08-27T14:00:24Z
dc.date.accessioned2025-10-08T08:36:24Z
dc.date.available2025-10-08T08:36:24Z
dc.date.issued01-08-2025
dc.identifier.urihttp://digilib.fisipol.ugm.ac.id/repo/handle/15717717/36251
dc.description.abstractCotton is a crucial economic crop, and timely and accurate acquisition of its spatial distribution information is of great significance for yield prediction, as well as for the formulation and adjustment of agricultural policies. To accurately and efficiently extract cotton cultivation areas at a large scale, in this study, we focused on the Santun River Irrigation District in Xinjiang as the research area. Utilizing Sentinel-2 satellite imagery from 2019 to 2024, four cotton extraction models—U-Net, SegNet, DeepLabV3+, and CBAM-UNet—were constructed. The models were evaluated using metrics, including the mean intersection over union (mIoU), precision, recall, F1-score, and over accuracy (OA), to assess the models’ performances in cotton extraction. The results demonstrate that the CBAM-UNet model achieved the highest accuracy, with an mIoU, precision, recall, F1-score, and OA of 84.02%, 88.99%, 94.75%, 91.78%, and 95.56%, respectively. The absolute error of the extracted cotton areas from 2019 to 2024 ranged between 923.69 and 1445.46 hm<sup>2</sup>, with absolute percentage errors of less than 10%. The coefficient of determination (R<sup>2</sup>) between the extracted results and statistical data was 0.9817, indicating the best fit. The findings of this study provide technical support for rapid cotton identification and extraction in large- and medium-sized irrigation districts.
dc.language.isoEN
dc.publisherMDPI AG
dc.subject.lccAgriculture (General)
dc.titleExtraction of Cotton Cultivation Areas Based on Deep Learning and Sentinel-2 Image Data
dc.typeArticle
dc.description.keywordscotton
dc.description.keywordsdeep learning
dc.description.keywordsattention mechanism
dc.description.keywordsCBAM-UNet
dc.description.doi10.3390/agriculture15161783
dc.title.journalAgriculture
dc.identifier.e-issn2077-0472
dc.identifier.oaioai:doaj.org/journal:9ca5b406d4af4596ad25b78b94b1bc1b
dc.journal.infoVolume 15, Issue 16


This item appears in the following Collection(s)

Show simple item record