A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data
In the face of global population growth and climate change, the protection and rational utilization of cropland are crucial for food security and ecological balance. However, the complex topography and unique ecological environment of the Qinghai-Tibet Plateau results in a lack of high-precision cro...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/21/4071 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173182695833600 |
|---|---|
| author | Huiling Chen Guojin He Xueli Peng Guizhou Wang Ranyu Yin |
| author_facet | Huiling Chen Guojin He Xueli Peng Guizhou Wang Ranyu Yin |
| author_sort | Huiling Chen |
| collection | DOAJ |
| description | In the face of global population growth and climate change, the protection and rational utilization of cropland are crucial for food security and ecological balance. However, the complex topography and unique ecological environment of the Qinghai-Tibet Plateau results in a lack of high-precision cropland monitoring data. Therefore, this paper constructs a high-quality cropland dataset for the YarlungZangbo-Lhasa-Nyangqv River region of the Qinghai-Tibet Plateau and proposes an MSC-ResUNet model for cropland extraction based on Landsat data. The dataset is annotated at the pixel level, comprising 61 Landsat 8 images in 2023. The MSC-ResUNet model innovatively combines multiscale features through residual connections and multiscale skip connections, effectively capturing features ranging from low-level spatial details to high-level semantic information and further enhances performance by incorporating depthwise separable convolutions as part of the feature fusion process. Experimental results indicate that MSC-ResUNet achieves superior accuracy compared to other models, with F1 scores of 0.826 and 0.856, and MCC values of 0.816 and 0.847, in regional robustness and temporal transferability tests, respectively. Performance analysis across different months and band combinations demonstrates that the model maintains high recognition accuracy during both growing and non-growing seasons, despite the study area’s complex landforms and diverse crops. |
| format | Article |
| id | doaj-art-92c1fc7d5ae54294b46da5e8a30f30f4 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-92c1fc7d5ae54294b46da5e8a30f30f42024-11-08T14:40:43ZengMDPI AGRemote Sensing2072-42922024-10-011621407110.3390/rs16214071A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat DataHuiling Chen0Guojin He1Xueli Peng2Guizhou Wang3Ranyu Yin4Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaIn the face of global population growth and climate change, the protection and rational utilization of cropland are crucial for food security and ecological balance. However, the complex topography and unique ecological environment of the Qinghai-Tibet Plateau results in a lack of high-precision cropland monitoring data. Therefore, this paper constructs a high-quality cropland dataset for the YarlungZangbo-Lhasa-Nyangqv River region of the Qinghai-Tibet Plateau and proposes an MSC-ResUNet model for cropland extraction based on Landsat data. The dataset is annotated at the pixel level, comprising 61 Landsat 8 images in 2023. The MSC-ResUNet model innovatively combines multiscale features through residual connections and multiscale skip connections, effectively capturing features ranging from low-level spatial details to high-level semantic information and further enhances performance by incorporating depthwise separable convolutions as part of the feature fusion process. Experimental results indicate that MSC-ResUNet achieves superior accuracy compared to other models, with F1 scores of 0.826 and 0.856, and MCC values of 0.816 and 0.847, in regional robustness and temporal transferability tests, respectively. Performance analysis across different months and band combinations demonstrates that the model maintains high recognition accuracy during both growing and non-growing seasons, despite the study area’s complex landforms and diverse crops.https://www.mdpi.com/2072-4292/16/21/4071croplandYarlungzangbo-Lhasa-Nyangqv River regiondeep learningmulti-scale featurelandsat datatraining dataset |
| spellingShingle | Huiling Chen Guojin He Xueli Peng Guizhou Wang Ranyu Yin A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data Remote Sensing cropland Yarlungzangbo-Lhasa-Nyangqv River region deep learning multi-scale feature landsat data training dataset |
| title | A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data |
| title_full | A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data |
| title_fullStr | A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data |
| title_full_unstemmed | A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data |
| title_short | A Multi-Scale Feature Fusion Deep Learning Network for the Extraction of Cropland Based on Landsat Data |
| title_sort | multi scale feature fusion deep learning network for the extraction of cropland based on landsat data |
| topic | cropland Yarlungzangbo-Lhasa-Nyangqv River region deep learning multi-scale feature landsat data training dataset |
| url | https://www.mdpi.com/2072-4292/16/21/4071 |
| work_keys_str_mv | AT huilingchen amultiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT guojinhe amultiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT xuelipeng amultiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT guizhouwang amultiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT ranyuyin amultiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT huilingchen multiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT guojinhe multiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT xuelipeng multiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT guizhouwang multiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata AT ranyuyin multiscalefeaturefusiondeeplearningnetworkfortheextractionofcroplandbasedonlandsatdata |