Monitoring Abandoned Cropland in Fragmented Mountainous Landscapes Based on the ML-LandTrendr Framework

Мониторинг заброшенных сельскохозяйственных угодий во фрагментированных горных ландшафтах на основе платформы ML-LandTrendr
Huaiyong Shao, Yue Wang, Jichong Han, Zhongyuan Xie, Xiaofei Sun, Long Ling, Jiamei Long, Ying Lin, Liangliang Zhang
2026-05-13

GeodetectorML-LandTrendr frameworkcropland abandonmentrandom foresttime-series analysis
Cropland abandonment is increasing in the upper and middle Yangtze River Basin due to complex terrain, urbanization, and labor migration. This threatens regional food security. To address the challenge of monitoring abandonment in fragmented hilly areas, we developed a framework. We integrated machine learning with time-series analysis. We mapped cropland probability using multi-source remote sensing data, random forest, and kernel density estimation, then applied LandTrendr to detect land-use changes and track the spatiotemporal evolution of abandonment from 2000 to 2022. Next, we combined Geodetector and linear regression to identify driving factors. The results show that abandoned cropland exhibited an increasing trend from 2000 to 2010, with an average annual growth rate of 20.4%. From 2010 to 2013, the area of abandoned cropland declined rapidly, decreasing by 44.6%. Between 2013 and 2022, abandoned cropland decreased steadily, with an average annual reduction rate of 24.7%. Spatially, abandonment was clustered in the central mountains and southern hills. Key drivers included distance to towns (DtT), total grain output (GTO), and GDP. Our approach supports cropland management and rural revitalization in regions with complex terrain.
1
Abandoned cropland declined rapidly by 44.6% between 2010 and 2013, then decreased steadily from 2013 to 2022 at an average annual rate of 24.7%.
2
Abandoned cropland increased from 2000 to 2010, with an average annual growth rate of 20.4%.
3
Abandonment was spatially concentrated in the central mountains and southern hills of the upper and middle Yangtze River Basin.
4
Distance to towns, total grain output, and GDP were identified as key factors driving cropland abandonment.
5
The ML-LandTrendr framework integrates multi-source remote sensing, random forest, kernel density estimation, and time-series change detection to monitor fragmented mountainous cropland.
6
The framework provides support for cropland management and rural revitalization in complex mountainous terrain.

Abandoned cropland in fragmented mountainous and hilly areas of the upper and middle Yangtze River Basin

The spatiotemporal dynamics and driving factors of cropland abandonment from 2000 to 2022

Publication Details
Publication Date
2026-05-13
Journal
Publisher
ISSN
Cited by
1
Access Type
Author Information
Authors
Huaiyong Shao
Yue Wang
Jichong Han
Zhongyuan Xie
Xiaofei Sun
Long Ling
Jiamei Long
Ying Lin
Liangliang Zhang
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%