Annual cropland change detection in arid areas with long time series remote sensing images: A case study of the economic belt of the north Tianshan Mountains, Xinjiang Province, China
Wang, Zhipan ， Wu, Yankun ， Luo, Cheng ， Wang, Weiwei ， Zhang, Qingling
2026-02-01 JOURNAL OF ARID ENVIRONMENTS 2026 232(卷), null(期), (null页)
JCR分区:
影响因子:
The increasing population and limited land supply pose serious challenges to sustainable development in arid regions. Monitoring dynamic cropland changes using remote sensing imagery can provide critical data to support policy-making and promote high-quality development in these areas. However, current approaches are often constrained by complex algorithm design and a heavy reliance on training samples. In this study, we propose an unsupervised annual cropland change detection algorithm that is sufficiently simple to operate efficiently on the Google Earth Engine (GEE) cloud platform. The economic belt of the North Tianshan Mountains region, a typical arid area, was chosen as the study area. The annual cropland change detection results demonstrated that the proposed method achieved overall accuracies of 79.5 % for cropland expansion and 80.4 % for cropland shrinkage, respectively. This method is cost-effective, unbiased, and readily scalable to national or global arid regions, and it can also deliver essential data to support high-quality development in arid zones. The source code of this study is available at: https://github.com/wzp8023391/Annual-cropland-change-detection.
相关推荐
- Mapping wilderness aesthetics on the Tibetan Plateau: an integrated deep learning and geospatial approach [2026-02-01]
- Deep soil depletion and edge compensation: Insights into optimized strategies for addressing water imbalance in arid-region plantations [2026-02-01]
- Exploring the Causes of Severe Fluctuations in Water Surface Area Using Water Index and Structural Equation Modeling: Evidence from Ebinur Lake, China [2026-02-01]
- Phenotypic plasticity of bread wheat contributes to yield reliability under heat and drought stress [2026-02-01]
- Refining Water Body Extraction by Remote Sensing With Deep Learning Models: Exploring Different Band Combinations [2026-02-01]