Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor

Timely and accurate crop mapping is crucial for providing essential data support for agricultural production management. Reliable ground truth samples form the foundation for crop mapping using remote sensing imagery, a task that presents significant challenges in regions with limited sample availab...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingjing Mai, Qisheng Feng, Shuai Fu, Ruijing Wang, Shuhui Zhang, Ruoqi Zhang, Tiangang Liang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/9/1494
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850278643480133632
author Jingjing Mai
Qisheng Feng
Shuai Fu
Ruijing Wang
Shuhui Zhang
Ruoqi Zhang
Tiangang Liang
author_facet Jingjing Mai
Qisheng Feng
Shuai Fu
Ruijing Wang
Shuhui Zhang
Ruoqi Zhang
Tiangang Liang
author_sort Jingjing Mai
collection DOAJ
description Timely and accurate crop mapping is crucial for providing essential data support for agricultural production management. Reliable ground truth samples form the foundation for crop mapping using remote sensing imagery, a task that presents significant challenges in regions with limited sample availability. To address this issue, this study evaluates instance-based transfer learning methods, using the Hexi Corridor as a case study to explore crop mapping strategies in areas with scarce samples. High-confidence pixels from the United States Cropland Data Layer (CDL), along with high-density time series data derived from Sentinel-1, Sentinel-2, and Landsat-8 satellite imagery, as well as key vegetation indices, were selected as training samples for the source domain. Various algorithms, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and TrAdaBoost, were employed to transfer knowledge from the source domain to the target domain for crop type mapping. The results demonstrated that during the transfer learning process using only source domain data—without utilizing any target domain data—the overall classification accuracy reached 73.88%, with optimal accuracies for maize and alfalfa at 88.97% and 85.23%, respectively. As target domain data were gradually incorporated, the total accuracy for all models ranged from 0.77 to 0.92, with F1-scores ranging from 0.76 to 0.92, showing a consistent improvement in model performance. This study highlights the feasibility of employing transfer learning for crop mapping in the Hexi Corridor, demonstrating its potential to reduce labeling costs for target domain samples and providing a valuable reference for crop mapping in regions with limited sample availability.
format Article
id doaj-art-9268a9205dd44c9a828c4b5fd0c41cdb
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-9268a9205dd44c9a828c4b5fd0c41cdb2025-08-20T01:49:24ZengMDPI AGRemote Sensing2072-42922025-04-01179149410.3390/rs17091494Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi CorridorJingjing Mai0Qisheng Feng1Shuai Fu2Ruijing Wang3Shuhui Zhang4Ruoqi Zhang5Tiangang Liang6State Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaState Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaState Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaState Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaState Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaState Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems, Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs, Engineering Research Center of Grassland Industry, Ministry of Education, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, ChinaTimely and accurate crop mapping is crucial for providing essential data support for agricultural production management. Reliable ground truth samples form the foundation for crop mapping using remote sensing imagery, a task that presents significant challenges in regions with limited sample availability. To address this issue, this study evaluates instance-based transfer learning methods, using the Hexi Corridor as a case study to explore crop mapping strategies in areas with scarce samples. High-confidence pixels from the United States Cropland Data Layer (CDL), along with high-density time series data derived from Sentinel-1, Sentinel-2, and Landsat-8 satellite imagery, as well as key vegetation indices, were selected as training samples for the source domain. Various algorithms, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and TrAdaBoost, were employed to transfer knowledge from the source domain to the target domain for crop type mapping. The results demonstrated that during the transfer learning process using only source domain data—without utilizing any target domain data—the overall classification accuracy reached 73.88%, with optimal accuracies for maize and alfalfa at 88.97% and 85.23%, respectively. As target domain data were gradually incorporated, the total accuracy for all models ranged from 0.77 to 0.92, with F1-scores ranging from 0.76 to 0.92, showing a consistent improvement in model performance. This study highlights the feasibility of employing transfer learning for crop mapping in the Hexi Corridor, demonstrating its potential to reduce labeling costs for target domain samples and providing a valuable reference for crop mapping in regions with limited sample availability.https://www.mdpi.com/2072-4292/17/9/1494transfer learningcrop mappingCDLrandom forestXGBoostTrAdaBoost
spellingShingle Jingjing Mai
Qisheng Feng
Shuai Fu
Ruijing Wang
Shuhui Zhang
Ruoqi Zhang
Tiangang Liang
Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
Remote Sensing
transfer learning
crop mapping
CDL
random forest
XGBoost
TrAdaBoost
title Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
title_full Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
title_fullStr Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
title_full_unstemmed Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
title_short Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor
title_sort enhancing crop type mapping in data scarce regions through transfer learning a case study of the hexi corridor
topic transfer learning
crop mapping
CDL
random forest
XGBoost
TrAdaBoost
url https://www.mdpi.com/2072-4292/17/9/1494
work_keys_str_mv AT jingjingmai enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT qishengfeng enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT shuaifu enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT ruijingwang enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT shuhuizhang enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT ruoqizhang enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor
AT tiangangliang enhancingcroptypemappingindatascarceregionsthroughtransferlearningacasestudyofthehexicorridor