Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification

Large-scale model transfer facilitates crop classification in unlabeled sample regions. However, due to the spectral differences in the satellite image time series (SITS) of the same crop type caused by variations in a crop-growing environment between regions, cross-regional model transfer faces imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Hengbin Wang, Yu Yao, Junyi Liu, Xindan Zhang, Yuanyuan Zhao, Shaoming Li, Zhe Liu, Xiaodong Zhang, Yelu Zeng
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Journal of Remote Sensing
Online Access:https://spj.science.org/doi/10.34133/remotesensing.0439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718541887995904
author Hengbin Wang
Yu Yao
Junyi Liu
Xindan Zhang
Yuanyuan Zhao
Shaoming Li
Zhe Liu
Xiaodong Zhang
Yelu Zeng
author_facet Hengbin Wang
Yu Yao
Junyi Liu
Xindan Zhang
Yuanyuan Zhao
Shaoming Li
Zhe Liu
Xiaodong Zhang
Yelu Zeng
author_sort Hengbin Wang
collection DOAJ
description Large-scale model transfer facilitates crop classification in unlabeled sample regions. However, due to the spectral differences in the satellite image time series (SITS) of the same crop type caused by variations in a crop-growing environment between regions, cross-regional model transfer faces important challenges. Given that models trained in the source domain are affected by SITS variations and perform poorly in the target domain, in this paper, we propose an unsupervised domain adaptation method based on climate indicator discrepancy (ClimID-UDA), which addresses the problem of cross-region model transfer by mitigating SITS discrepancies using climate indicator discrepancy. In ClimID-UDA, we selected 6 climate variables representing the conditions of light, heat, water, and pressure and then constructed an index called climate indicator by calculating the barycenter of the 6 climate variables. Finally, climate indicator discrepancy was used to correct the SITS of the target domain to adapt the model trained in the source domain. The proposed method was tested in 4 regions in both China and Europe. The experiments covered different satellite sensors, different classification models, and different years. The experimental results show that ClimID-UDA achieves a more than 11% improvement in average accuracy and provides a viable option for large-scale cross-regional model transfer.
format Article
id doaj-art-6187f2bcd2a041d5abda596f436cc09b
institution DOAJ
issn 2694-1589
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Journal of Remote Sensing
spelling doaj-art-6187f2bcd2a041d5abda596f436cc09b2025-08-20T03:12:20ZengAmerican Association for the Advancement of Science (AAAS)Journal of Remote Sensing2694-15892025-01-01510.34133/remotesensing.0439Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop ClassificationHengbin Wang0Yu Yao1Junyi Liu2Xindan Zhang3Yuanyuan Zhao4Shaoming Li5Zhe Liu6Xiaodong Zhang7Yelu Zeng8College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.College of Land Science and Technology, China Agricultural University, Beijing, China.Large-scale model transfer facilitates crop classification in unlabeled sample regions. However, due to the spectral differences in the satellite image time series (SITS) of the same crop type caused by variations in a crop-growing environment between regions, cross-regional model transfer faces important challenges. Given that models trained in the source domain are affected by SITS variations and perform poorly in the target domain, in this paper, we propose an unsupervised domain adaptation method based on climate indicator discrepancy (ClimID-UDA), which addresses the problem of cross-region model transfer by mitigating SITS discrepancies using climate indicator discrepancy. In ClimID-UDA, we selected 6 climate variables representing the conditions of light, heat, water, and pressure and then constructed an index called climate indicator by calculating the barycenter of the 6 climate variables. Finally, climate indicator discrepancy was used to correct the SITS of the target domain to adapt the model trained in the source domain. The proposed method was tested in 4 regions in both China and Europe. The experiments covered different satellite sensors, different classification models, and different years. The experimental results show that ClimID-UDA achieves a more than 11% improvement in average accuracy and provides a viable option for large-scale cross-regional model transfer.https://spj.science.org/doi/10.34133/remotesensing.0439
spellingShingle Hengbin Wang
Yu Yao
Junyi Liu
Xindan Zhang
Yuanyuan Zhao
Shaoming Li
Zhe Liu
Xiaodong Zhang
Yelu Zeng
Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
Journal of Remote Sensing
title Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
title_full Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
title_fullStr Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
title_full_unstemmed Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
title_short Unsupervised Cross-Regional and Cross-Year Adaptation by Climate Indicator Discrepancy for Crop Classification
title_sort unsupervised cross regional and cross year adaptation by climate indicator discrepancy for crop classification
url https://spj.science.org/doi/10.34133/remotesensing.0439
work_keys_str_mv AT hengbinwang unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT yuyao unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT junyiliu unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT xindanzhang unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT yuanyuanzhao unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT shaomingli unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT zheliu unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT xiaodongzhang unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification
AT yeluzeng unsupervisedcrossregionalandcrossyearadaptationbyclimateindicatordiscrepancyforcropclassification