A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China
Arable land is the fundamental guarantee of agricultural production, and accessing accurate arable land information is particularly crucial. A novel deep learning model named CNX-eMLP with ConvNeXt as the backbone and an enhanced Multilayer Perceptron (eMLP) as the decoder was proposed for arable la...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-01-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2024.2400493 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846129161052094464 |
|---|---|
| author | Yanxi Chen Xingzhu Xiao Yongle Zhang Min Huang Ziyi Tang Hao Li |
| author_facet | Yanxi Chen Xingzhu Xiao Yongle Zhang Min Huang Ziyi Tang Hao Li |
| author_sort | Yanxi Chen |
| collection | DOAJ |
| description | Arable land is the fundamental guarantee of agricultural production, and accessing accurate arable land information is particularly crucial. A novel deep learning model named CNX-eMLP with ConvNeXt as the backbone and an enhanced Multilayer Perceptron (eMLP) as the decoder was proposed for arable land extraction. The model was employed to extract arable land using high-resolution satellite imagery in a case study at Pengxi County of Southwest China and compared its performance with six deep learning models, a machine learning-based algorithm, and SinoLC-1. The study results show the CNX-eMLP significantly achieved the highest accuracy, with MIoU and OA of 75.21 and 87.9, highlighting a trade-off between computational complexity and accuracy. The CNX-eMLP model reveals arable land is predominantly found in low-altitude areas (below 400 m), with most plots being 0-5 hectares. The study presents an efficient and feasible method for accurate high-resolution remote sensing monitoring of arable land parcels in hilly regions. |
| format | Article |
| id | doaj-art-42ae19afff3141d89ebc3f9a5d2d9b07 |
| institution | Kabale University |
| issn | 1010-6049 1752-0762 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj-art-42ae19afff3141d89ebc3f9a5d2d9b072024-12-10T08:23:08ZengTaylor & Francis GroupGeocarto International1010-60491752-07622024-01-0139110.1080/10106049.2024.2400493A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest ChinaYanxi Chen0Xingzhu Xiao1Yongle Zhang2Min Huang3Ziyi Tang4Hao Li5College of Resources, Sichuan Agricultural University, Chengdu, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu, ChinaArable land is the fundamental guarantee of agricultural production, and accessing accurate arable land information is particularly crucial. A novel deep learning model named CNX-eMLP with ConvNeXt as the backbone and an enhanced Multilayer Perceptron (eMLP) as the decoder was proposed for arable land extraction. The model was employed to extract arable land using high-resolution satellite imagery in a case study at Pengxi County of Southwest China and compared its performance with six deep learning models, a machine learning-based algorithm, and SinoLC-1. The study results show the CNX-eMLP significantly achieved the highest accuracy, with MIoU and OA of 75.21 and 87.9, highlighting a trade-off between computational complexity and accuracy. The CNX-eMLP model reveals arable land is predominantly found in low-altitude areas (below 400 m), with most plots being 0-5 hectares. The study presents an efficient and feasible method for accurate high-resolution remote sensing monitoring of arable land parcels in hilly regions.https://www.tandfonline.com/doi/10.1080/10106049.2024.2400493Deep learningnovel arable land extraction modelhigh-resolution remote sensing imagessemantic segmentationtexture features |
| spellingShingle | Yanxi Chen Xingzhu Xiao Yongle Zhang Min Huang Ziyi Tang Hao Li A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China Geocarto International Deep learning novel arable land extraction model high-resolution remote sensing images semantic segmentation texture features |
| title | A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China |
| title_full | A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China |
| title_fullStr | A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China |
| title_full_unstemmed | A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China |
| title_short | A novel deep learning model for extracting arable land from high-resolution remote sensing images in hilly areas: a case study in the Sichuan Basin of Southwest China |
| title_sort | novel deep learning model for extracting arable land from high resolution remote sensing images in hilly areas a case study in the sichuan basin of southwest china |
| topic | Deep learning novel arable land extraction model high-resolution remote sensing images semantic segmentation texture features |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2024.2400493 |
| work_keys_str_mv | AT yanxichen anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT xingzhuxiao anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT yonglezhang anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT minhuang anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT ziyitang anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT haoli anoveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT yanxichen noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT xingzhuxiao noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT yonglezhang noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT minhuang noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT ziyitang noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina AT haoli noveldeeplearningmodelforextractingarablelandfromhighresolutionremotesensingimagesinhillyareasacasestudyinthesichuanbasinofsouthwestchina |