Monitoring Cropland Abandonment in Hilly Areas with Sentinel-1 and Sentinel-2 Timeseries

Мониторинг заброшенности сельскохозяйственных угодий в холмистой местности с использованием временных рядов Sentinel-1 и Sentinel-2
Shan He, Huaiyong Shao, Wei Xian, Ziqiang Yin, You Meng, Jialong Zhong, Jiaguo Qi
2022-08-07

Cropland abandonmentHilly areasLand-cover trajectoriesRandom forest classifierSentinel-1 and Sentinel-2 time series
Abandoned cropland may lead to a series of issues regarding the environment, ecology, and food security. In hilly areas, cropland is prone to be abandoned due to scattered planting, relatively fewer sunlight hours, and a lower agricultural input–output ratio. Furthermore, the impact of abandoned rainfed cropland differs from abandoned irrigated cropland; thus, the corresponding land strategies vary accordingly. Unfortunately, monitoring abandoned cropland is still an enormous challenge in hilly areas. In this study, a new approach was proposed by (1) improving the availability of Sentinel-1 and Sentinel-2 images by a series of processes, (2) obtaining training samples from multisource data overlay analysis and timeseries viewer tool, (3) mapping annual land cover from all available Sentinel-1 and Sentinel-2 images, training samples, and the random forest classifier, and (4) mapping the spatiotemporal distribution of abandoned rainfed cropland and irrigated cropland in hilly areas by assessing land-cover trajectories along with time. The result showed that rainfed cropland had lower F1 scores (0.759 to 0.8) compared to that irrigated cropland (0.836 to 0.879). High overall accuracies of around 0.90 were achieved, with the kappa values ranging from 0.851 to 0.862, which outperformed the existing products in accuracy and spatial detail. Our study provides a reference for extracting the spatiotemporal distribution of abandoned rainfed cropland and irrigated cropland in hilly areas.
1
A Sentinel-1/Sentinel-2 time-series approach maps annual land cover and distinguishes abandoned rainfed from abandoned irrigated cropland in hilly areas.
2
Land-cover trajectories enable assessment of the spatiotemporal distribution of cropland abandonment and support differentiated strategies for rainfed and irrigated land.
3
Overall accuracies were approximately 0.90, with kappa values of 0.851–0.862, outperforming existing products in accuracy and spatial detail.
4
Rainfed cropland classification achieved lower F1 scores of 0.759–0.800 than irrigated cropland, which achieved 0.836–0.879.
5
The method improves satellite-image availability, derives training samples through multisource overlay and time-series inspection, and classifies land cover using random forests.

abandoned rainfed and irrigated cropland in hilly areas

the spatiotemporal distribution and monitoring accuracy of cropland abandonment, differentiated by rainfed versus irrigated cropland

Publication Details
Publication Date
2022-08-07
Journal
Remote Sensing
Publisher
Multidisciplinary Digital Publishing Institute
ISSN
2072-4292
Cited by
36
Access Type
Author Information
Authors
Shan He
Huaiyong Shao
Wei Xian
Ziqiang Yin
You Meng
Jialong Zhong
Jiaguo Qi
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%