Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China
Long-term, large-scale crop distribution mapping is crucial for agricultural policy and resource management. While high-resolution multispectral remote sensing has been widely used for crop type mapping, three major challenges remain: 1) spatiotemporal heterogeneity in cloud-free and shadow-free obs...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225003140 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849687993632161792 |
|---|---|
| author | Longcai Zhao Taifeng Dong Xin Du Bing Dong Qiangzi Li |
| author_facet | Longcai Zhao Taifeng Dong Xin Du Bing Dong Qiangzi Li |
| author_sort | Longcai Zhao |
| collection | DOAJ |
| description | Long-term, large-scale crop distribution mapping is crucial for agricultural policy and resource management. While high-resolution multispectral remote sensing has been widely used for crop type mapping, three major challenges remain: 1) spatiotemporal heterogeneity in cloud-free and shadow-free observations, 2) the lack of sufficient ground truth samples, and 3) limited generalization of identification models over extended periods. To address these challenges, this paper constructs a time-continuous sequence model that captures the unique feature pattern between the target-crop and non-target crops (referred to as the knowledge model). Specifically, a morphing approach was first employed to interpolate intermediate models between two pre-trained non-adjacent knowledge models. Then, a date-continuous sequence model that estimate the probabilistic of growth patterns of target crop was generated. This date-continuous sequence model mitigates spatiotemporal heterogeneity issues at the pixel level across large regions. Additionally, crop-specific knowledge model addresses sample scarcity and enhances generalization during long-term applications. The method was test using a long-term cotton mapping task (2000, 2005–2023) in Xinjiang, China. The results demonstrate that: 1) The sequence of knowledge model can effectively capture feature differences between cotton and non-cotton throughout the growing period, resulting in knowledge feature has a higher separability compared to original spectral and vegetation index features; 2) Segmenting knowledge features with Unet enables effective mapping cotton and non-cotton without ground samples. The estimated planting area from our mapping results shows excellent consistency with official statistics (R2 = 0.97). The correlation between our 2018–2021 results and previously published data reached 0.8, 0.88, 0.88, and 0.89. 3). The stable and excellent mapping accuracy proves that resonation of connectivity and reachability in parameter space between two networks with identical architecture, and model morphing is a feasible way to overcome the spatial–temporal heterogeneity in valid observations in large regions. |
| format | Article |
| id | doaj-art-0f9dbd30fed947bd809fa4d2d53ee12a |
| institution | DOAJ |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-0f9dbd30fed947bd809fa4d2d53ee12a2025-08-20T03:22:11ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-07-0114110466710.1016/j.jag.2025.104667Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, ChinaLongcai Zhao0Taifeng Dong1Xin Du2Bing Dong3Qiangzi Li4College of Resources and Environment, Northwest A&F University, Yangling 712100 Shaanxi, ChinaNational Wildlife Research Centre, Environment and Climate Change Canada, 1125 Colonel By Drive, Ottawa, ON K1A0H3, CanadaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCollege of Resources and Environment, Northwest A&F University, Yangling 712100 Shaanxi, China; Corresponding authors.Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; Corresponding authors.Long-term, large-scale crop distribution mapping is crucial for agricultural policy and resource management. While high-resolution multispectral remote sensing has been widely used for crop type mapping, three major challenges remain: 1) spatiotemporal heterogeneity in cloud-free and shadow-free observations, 2) the lack of sufficient ground truth samples, and 3) limited generalization of identification models over extended periods. To address these challenges, this paper constructs a time-continuous sequence model that captures the unique feature pattern between the target-crop and non-target crops (referred to as the knowledge model). Specifically, a morphing approach was first employed to interpolate intermediate models between two pre-trained non-adjacent knowledge models. Then, a date-continuous sequence model that estimate the probabilistic of growth patterns of target crop was generated. This date-continuous sequence model mitigates spatiotemporal heterogeneity issues at the pixel level across large regions. Additionally, crop-specific knowledge model addresses sample scarcity and enhances generalization during long-term applications. The method was test using a long-term cotton mapping task (2000, 2005–2023) in Xinjiang, China. The results demonstrate that: 1) The sequence of knowledge model can effectively capture feature differences between cotton and non-cotton throughout the growing period, resulting in knowledge feature has a higher separability compared to original spectral and vegetation index features; 2) Segmenting knowledge features with Unet enables effective mapping cotton and non-cotton without ground samples. The estimated planting area from our mapping results shows excellent consistency with official statistics (R2 = 0.97). The correlation between our 2018–2021 results and previously published data reached 0.8, 0.88, 0.88, and 0.89. 3). The stable and excellent mapping accuracy proves that resonation of connectivity and reachability in parameter space between two networks with identical architecture, and model morphing is a feasible way to overcome the spatial–temporal heterogeneity in valid observations in large regions.http://www.sciencedirect.com/science/article/pii/S1569843225003140Remote SensingCrop TypeKnowledge FeatureDeep LearningCotton |
| spellingShingle | Longcai Zhao Taifeng Dong Xin Du Bing Dong Qiangzi Li Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China International Journal of Applied Earth Observations and Geoinformation Remote Sensing Crop Type Knowledge Feature Deep Learning Cotton |
| title | Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China |
| title_full | Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China |
| title_fullStr | Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China |
| title_full_unstemmed | Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China |
| title_short | Model morphing supported large scale crop type mapping: A case stuy of cotton mapping in Xinjiang, China |
| title_sort | model morphing supported large scale crop type mapping a case stuy of cotton mapping in xinjiang china |
| topic | Remote Sensing Crop Type Knowledge Feature Deep Learning Cotton |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225003140 |
| work_keys_str_mv | AT longcaizhao modelmorphingsupportedlargescalecroptypemappingacasestuyofcottonmappinginxinjiangchina AT taifengdong modelmorphingsupportedlargescalecroptypemappingacasestuyofcottonmappinginxinjiangchina AT xindu modelmorphingsupportedlargescalecroptypemappingacasestuyofcottonmappinginxinjiangchina AT bingdong modelmorphingsupportedlargescalecroptypemappingacasestuyofcottonmappinginxinjiangchina AT qiangzili modelmorphingsupportedlargescalecroptypemappingacasestuyofcottonmappinginxinjiangchina |