Identification of Abandoned Cropland and Global–Local Driving Mechanism Analysis via Multi-Source Remote Sensing Data and Multi-Objective Optimization

Идентификация заброшенных сельскохозяйственных угодий и анализ глобально-локальных механизмов воздействия на основе многoисточниковых данных дистанционного зондирования и многокритериальной оптимизации
Side Gui, Jiaming Li, Guoping Chen, Junsan Zhao, Bo‐Hui Tang, Lei Li
2025-09-04

Google Earth EngineNSGA-II-XGBoostSHAP and LIME interpretabilityabandoned cropland identificationmulti-source remote sensing
The issue of abandoned cropland poses a significant threat to national food security and the sustainable use of land resources, highlighting the urgent need for an efficient and interpretable remote sensing identification framework. This study integrates three authoritative land cover datasets—the European Space Agency WorldCover (ESA), the Environmental Systems Research Institute Land Cover (ESRI), and the China Resource and Environment Data Cloud Platform (CRLC). Multi-source remote sensing features were extracted using the Google Earth Engine platform, and high-quality training samples were constructed by randomly selecting sample points based on these features in ArcGIS. A recursive feature cross-validation method is employed to eliminate redundant variables, thereby optimizing the feature structure without compromising classification accuracy. In terms of model construction, a multi-objective optimization strategy combining the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and eXtreme Gradient Boosting (XGBoost) is proposed. By incorporating a pruning mechanism, computational efficiency is significantly improved—accelerating the identification speed by up to 75%—while maintaining model accuracy (OA: 0.9817; Kappa: 0.9633; F1-score: 0.9817; recall: 0.9866). For result interpretation, the SHapley Additive exPlanations (SHAP) method is used to evaluate global feature importance, revealing that variables such as SAVG, B3_p25, Road, DEM, and Population contribute most significantly to the identification of abandoned cropland. Meanwhile, the Local Interpretable Model-Agnostic Explanations (LIME) method is applied to conduct local interpretability analysis on typical samples. The results show that, while some samples share consistent dominant features with the global results, others exhibit stronger local influences from features such as slope and SAVG. The combination of SHAP and LIME for global–local interpretability provides insight into the heterogeneous drivers of cropland abandonment and enhances the transparency of the classification model. This study presents a practical, scalable framework for the rapid identification and management of abandoned cropland, balancing precision, interpretability, and efficiency.
1
An NSGA-II–XGBoost multi-objective optimization framework with pruning accelerates abandoned-cropland identification by up to 75%.
2
Recursive feature cross-validation removes redundant variables and optimizes the feature structure without compromising classification accuracy.
3
SHAP identifies SAVG, B3_p25, road proximity, DEM, and population as the most influential global features, while LIME reveals sample-specific effects involving slope and SAVG.
4
The optimized model achieves OA 0.9817, Kappa 0.9633, F1-score 0.9817, and recall 0.9866.
5
The study integrates ESA WorldCover, ESRI, and CRLC datasets with Google Earth Engine features to identify abandoned cropland using remote sensing.

abandoned cropland

remote-sensing identification and global–local driving mechanisms of abandoned cropland, including the importance and heterogeneous local effects of environmental and socioeconomic features

Publication Details
Publication Date
2025-09-04
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Side Gui
Jiaming Li
Guoping Chen
Junsan Zhao
Bo‐Hui Tang
Lei Li
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%