CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation
Crop mapping is essential for agricultural management and food production monitoring, but challenges like limited crop labels and poor model generalization significantly hinder large-scale crop mapping. Here, we introduce a novel Contrastive Self-Training Network (CSTN), integrating a self-training...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225000263 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859374903263232 |
|---|---|
| author | Shuwen Peng Liqiang Zhang Rongchang Xie Ying Qu |
| author_facet | Shuwen Peng Liqiang Zhang Rongchang Xie Ying Qu |
| author_sort | Shuwen Peng |
| collection | DOAJ |
| description | Crop mapping is essential for agricultural management and food production monitoring, but challenges like limited crop labels and poor model generalization significantly hinder large-scale crop mapping. Here, we introduce a novel Contrastive Self-Training Network (CSTN), integrating a self-training strategy and contrastive domain adaptation (CDA) for cross-region crop mapping. CSTN uses pseudo-labels in the target region generated by the self-training strategy to assist supervised learning, and aligns features across regions using class-aware prototypes. Qualitative and quantitative evaluations demonstrate that CSTN significantly outperforms state-of-the-art methods with a 12.29 % increase in average F1-score, particularly in maize identification. Moreover, CSTN also enables early-season crop classification for pre-harvest decision-making applications. The interpretability of the model is demonstrated through an in-depth analysis of feature map visualizations, attention map visualizations, and the effectiveness of the modules. This study provides a robust method for enhancing large-scale crop mapping and facilitating more accurate and timely agricultural practices. |
| format | Article |
| id | doaj-art-0f9cf374383d4c758da4b8444a6ddc1b |
| institution | Kabale University |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-0f9cf374383d4c758da4b8444a6ddc1b2025-02-11T04:33:42ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-01136104379CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptationShuwen Peng0Liqiang Zhang1Rongchang Xie2Ying Qu3State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875 ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875 ChinaCenter for Data Science, Peking University, Beijing 100871 ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875 China; Corresponding author.Crop mapping is essential for agricultural management and food production monitoring, but challenges like limited crop labels and poor model generalization significantly hinder large-scale crop mapping. Here, we introduce a novel Contrastive Self-Training Network (CSTN), integrating a self-training strategy and contrastive domain adaptation (CDA) for cross-region crop mapping. CSTN uses pseudo-labels in the target region generated by the self-training strategy to assist supervised learning, and aligns features across regions using class-aware prototypes. Qualitative and quantitative evaluations demonstrate that CSTN significantly outperforms state-of-the-art methods with a 12.29 % increase in average F1-score, particularly in maize identification. Moreover, CSTN also enables early-season crop classification for pre-harvest decision-making applications. The interpretability of the model is demonstrated through an in-depth analysis of feature map visualizations, attention map visualizations, and the effectiveness of the modules. This study provides a robust method for enhancing large-scale crop mapping and facilitating more accurate and timely agricultural practices.http://www.sciencedirect.com/science/article/pii/S1569843225000263Crop mappingSatellite imagery time seriesPseudo-labelsContrastive Domain AdaptationModel interpretability |
| spellingShingle | Shuwen Peng Liqiang Zhang Rongchang Xie Ying Qu CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation International Journal of Applied Earth Observations and Geoinformation Crop mapping Satellite imagery time series Pseudo-labels Contrastive Domain Adaptation Model interpretability |
| title | CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation |
| title_full | CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation |
| title_fullStr | CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation |
| title_full_unstemmed | CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation |
| title_short | CSTN: A cross-region crop mapping method integrating self-training and contrastive domain adaptation |
| title_sort | cstn a cross region crop mapping method integrating self training and contrastive domain adaptation |
| topic | Crop mapping Satellite imagery time series Pseudo-labels Contrastive Domain Adaptation Model interpretability |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225000263 |
| work_keys_str_mv | AT shuwenpeng cstnacrossregioncropmappingmethodintegratingselftrainingandcontrastivedomainadaptation AT liqiangzhang cstnacrossregioncropmappingmethodintegratingselftrainingandcontrastivedomainadaptation AT rongchangxie cstnacrossregioncropmappingmethodintegratingselftrainingandcontrastivedomainadaptation AT yingqu cstnacrossregioncropmappingmethodintegratingselftrainingandcontrastivedomainadaptation |