A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China
Rapeseed mapping is crucial for refined agricultural management and food security. However, existing remote sensing-based methods for rapeseed mapping in Southwest China are severely limited by insufficient training samples and persistent cloud cover. To address the above challenges, this study pres...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/14/1/200 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588162408382464 |
|---|---|
| author | Ruolan Jiang Xingyin Duan Song Liao Ziyi Tang Hao Li |
| author_facet | Ruolan Jiang Xingyin Duan Song Liao Ziyi Tang Hao Li |
| author_sort | Ruolan Jiang |
| collection | DOAJ |
| description | Rapeseed mapping is crucial for refined agricultural management and food security. However, existing remote sensing-based methods for rapeseed mapping in Southwest China are severely limited by insufficient training samples and persistent cloud cover. To address the above challenges, this study presents an automatic rapeseed mapping framework that integrates multi-source remote sensing data fusion, automated sample generation, and deep learning models. The framework was applied in Santai County, Sichuan Province, Southwest China, which has typical topographical and climatic characteristics. First, MODIS and Landsat data were used to fill the gaps in Sentinel-2 imagery, creating time-series images through the object-level processing version of the spatial and temporal adaptive reflectance fusion model (OL-STARFM). In addition, a novel spectral phenology approach was developed to automatically generate training samples, which were then input into the improved TS-ConvNeXt ECAPA-TDNN (NeXt-TDNN) deep learning model for accurate rapeseed mapping. The results demonstrated that the OL-STARFM approach was effective in rapeseed mapping. The proposed automated sample generation method proved effective in producing reliable rapeseed samples, achieving a low Dynamic Time Warping (DTW) distance (<0.81) when compared to field samples. The NeXt-TDNN model showed an overall accuracy (OA) of 90.12% and a mean Intersection over Union (mIoU) of 81.96% in Santai County, outperforming other models such as random forest, XGBoost, and UNet-LSTM. These results highlight the effectiveness of the proposed automatic rapeseed mapping framework in accurately identifying rapeseed. This framework offers a valuable reference for monitoring other crops in similar environments. |
| format | Article |
| id | doaj-art-d294b797e5764c4e8769d6ded3bd1752 |
| institution | Kabale University |
| issn | 2073-445X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj-art-d294b797e5764c4e8769d6ded3bd17522025-01-24T13:38:18ZengMDPI AGLand2073-445X2025-01-0114120010.3390/land14010200A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest ChinaRuolan Jiang0Xingyin Duan1Song Liao2Ziyi Tang3Hao Li4College of Resources, Sichuan Agricultural University, Chengdu 611130, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu 611130, ChinaPrecision Forestry Key Laboratory of Beijing, Beijing Forestry University, Beijing 100083, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu 611130, ChinaCollege of Resources, Sichuan Agricultural University, Chengdu 611130, ChinaRapeseed mapping is crucial for refined agricultural management and food security. However, existing remote sensing-based methods for rapeseed mapping in Southwest China are severely limited by insufficient training samples and persistent cloud cover. To address the above challenges, this study presents an automatic rapeseed mapping framework that integrates multi-source remote sensing data fusion, automated sample generation, and deep learning models. The framework was applied in Santai County, Sichuan Province, Southwest China, which has typical topographical and climatic characteristics. First, MODIS and Landsat data were used to fill the gaps in Sentinel-2 imagery, creating time-series images through the object-level processing version of the spatial and temporal adaptive reflectance fusion model (OL-STARFM). In addition, a novel spectral phenology approach was developed to automatically generate training samples, which were then input into the improved TS-ConvNeXt ECAPA-TDNN (NeXt-TDNN) deep learning model for accurate rapeseed mapping. The results demonstrated that the OL-STARFM approach was effective in rapeseed mapping. The proposed automated sample generation method proved effective in producing reliable rapeseed samples, achieving a low Dynamic Time Warping (DTW) distance (<0.81) when compared to field samples. The NeXt-TDNN model showed an overall accuracy (OA) of 90.12% and a mean Intersection over Union (mIoU) of 81.96% in Santai County, outperforming other models such as random forest, XGBoost, and UNet-LSTM. These results highlight the effectiveness of the proposed automatic rapeseed mapping framework in accurately identifying rapeseed. This framework offers a valuable reference for monitoring other crops in similar environments.https://www.mdpi.com/2073-445X/14/1/200deep learningimage fusionrapeseed mappingrule-based sample generation |
| spellingShingle | Ruolan Jiang Xingyin Duan Song Liao Ziyi Tang Hao Li A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China Land deep learning image fusion rapeseed mapping rule-based sample generation |
| title | A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China |
| title_full | A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China |
| title_fullStr | A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China |
| title_full_unstemmed | A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China |
| title_short | A Novel Rapeseed Mapping Framework Integrating Image Fusion, Automated Sample Generation, and Deep Learning in Southwest China |
| title_sort | novel rapeseed mapping framework integrating image fusion automated sample generation and deep learning in southwest china |
| topic | deep learning image fusion rapeseed mapping rule-based sample generation |
| url | https://www.mdpi.com/2073-445X/14/1/200 |
| work_keys_str_mv | AT ruolanjiang anovelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT xingyinduan anovelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT songliao anovelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT ziyitang anovelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT haoli anovelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT ruolanjiang novelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT xingyinduan novelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT songliao novelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT ziyitang novelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina AT haoli novelrapeseedmappingframeworkintegratingimagefusionautomatedsamplegenerationanddeeplearninginsouthwestchina |