Abandoned Cropland Mapping With Phenology-Enhanced Change Vector Analysis and Semi-Supervised Learning in Different Cropping Intensity Areas
Картографирование заброшенных сельскохозяйственных угодий с использованием анализа векторов изменений, усиленного фенологическими признаками, и полуобучения в районах с различной интенсивностью земледелия
2024-01-01
SCID: 54.1/jjjshrfq
Discuss with AI
abandoned cropland mappingco-training semi-supervised classificationland cover change detectionphenology-enhanced change vector analysisremote sensing
Figures from the paper
Abstract (AI)
Accurate information on the spatial and temporal distribution of abandoned cropland (AC) is crucial for protecting arable land, and maintaining regional food security and ecological stability. Nevertheless, the unavailability of dedicated monitoring for AC, along with the extended time frame required for remote sensing surveillance and the intricate transformation of land cover types following abandonment, poses considerable challenges in producing accurate AC maps for scientific purposes. To address these challenges, a new framework for AC identification was proposed. Specifically, the change detection was performed using the phenology-enhanced change vector analysis (PECVA) method, followed by a co-training semi-supervised classification method based on historical samples and sparse samples (HS-SSC) to classify the land cover type in change areas and obtain long-term land cover mapping results. Next, a land cover type change detector method was applied to identify the location and time of AC occurrences. Sufficient comparative experiments and accuracy validation were conducted to confirm the effectiveness of the PECVA and HS-SSC. The proposed method was verified in areas with single and double cropping per year, with average precision rates of 85.40% and 83.57% respectively for multi-year AC identification. This study offers a promising tool for identifying AC, which can aid in AC recultivation and serve for arable land conservation and land resource management. Our code is available at https://github.com/zhangtingting114/ACI.
Key Findings
1
A dedicated land-cover transition detector identifies both the locations and occurrence times of abandoned cropland.
2
A framework combines phenology-enhanced change vector analysis, semi-supervised classification, and land-cover change detection for abandoned cropland identification.
3
PECVA detects candidate land-cover changes, while HS-SSC uses historical and sparse samples to classify changed areas and generate long-term land-cover maps.
4
The approach provides a tool for abandoned-cropland recultivation, arable-land conservation, and land-resource management; implementation code is publicly available.
5
The framework was validated in single- and double-cropping regions, achieving average multi-year identification precisions of 85.40% and 83.57%, respectively.
Research Object
abandoned cropland in areas with different cropping intensities
Research Subject
the spatial and temporal identification of abandonment occurrences through long-term land-cover change mapping
Publication Details
Publication Date
2024-01-01
Journal
Publisher
ISSN
Cited by
9
Access Type
Author Information
Download PDF
Subscribe to digest