Journal of Integrative Agriculture ›› 2025, Vol. 24 ›› Issue (11): 4430-4450.DOI: 10.1016/j.jia.2025.04.021

• • 上一篇    下一篇

基于Landsat时间序列影像的黄土丘陵沟壑区撂荒耕地监测

  

  • 收稿日期:2024-11-28 修回日期:2025-04-18 接受日期:2025-03-24 出版日期:2025-11-20 发布日期:2025-10-17

Monitoring abandoned cropland in the hilly and gully regions of the Loess Plateau using Landsat time series images

Chenxiao Duan1, 2, 3, Jiabei Li1, 2, Shufang Wu1, 2#, Liming Yu4, Hao Feng2, Kadambot H M Siddique3   

  1. 1 Key Laboratory of Agricultural Soil and Water Engineering in Arid and Semiarid Areas of Ministry of Education, Northwest A&F University, Yangling 712100, China

    2 Institute of Water Saving Agriculture in Arid Areas of China, Northwest A&F University, Yangling 712100, China

    3 The UWA Institute of Agriculture, The University of Western Australia, Perth, WA 6001, Australia

    4 Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China

  • Received:2024-11-28 Revised:2025-04-18 Accepted:2025-03-24 Online:2025-11-20 Published:2025-10-17
  • About author:Chenxiao Duan, E-mail: dcxvayy00@163.com; #Correspondence Shufang Wu, Mobile: +86-13572267814, E-mail: wsfjs@163.com
  • Supported by:
    The work was supported by the National Key R&D Program of China (2023YFD1900300), the State Administration of Foreign Experts Affairs of China (B12007), and the 111 Project of China.  We also gratefully acknowledge the support by the China Scholarship Council (202306300092).

PDF

摘要：

耕地撂荒已成为全球性问题，对耕地可持续管理、国家粮食安全和生态环境保护等构成重大威胁。遥感技术对于大尺度区域内撂荒耕地的识别和监测至关重要，然而，目前关于黄土丘陵沟壑区撂荒耕地的有效识别方法和空间分布格局的研究较少。本研究基于2019-2021年Landsat-8影像，提出了土地利用轨迹和归一化植被指数（NDVI）时间序列法，对延河流域的撂荒耕地进行监测并分析其空间分布。结果表明，利用随机森林算法、可靠的土地覆盖样本和优化特征数据集可以实现高精度的年度土地利用分类。土地利用图的总体精度（OA）和Kappa系数分别超过90%和0.88，证明了三年以来分类的有效性。我们使用两种不同的变化检测方法对研究区的撂荒耕地进行识别，并评估其精度和有效性。土地利用轨迹法对撂荒耕地的提取效果优于NDVI时间序列法，其OA值为83.5%，F1值为84.7%。根据土地利用轨迹检测结果，2021年研究区的撂荒耕地面积为164.6 km2，撂荒率为16.3%。此外，耕地撂荒主要发生在自然条件恶劣的西北部，南部和东部地区的撂荒较少。地形地貌对撂荒耕地的空间分布有显著影响，撂荒耕地大多位于海拔较高、坡度较大的山区。撂荒率一般随着海拔和坡度的升高而增加。本研究结果为黄土丘陵沟壑区撂荒耕地识别方法的选择及其空间分布分析提供了有价值的参考和指导。我们提出的方法为类似复杂地形地区的撂荒耕地监测和优化土地利用变化检测提供了可靠的解决方案。

Abstract:

Cropland abandonment has become a global issue that poses significant threats to sustainable cropland management, national food security, and the ecological environment.  Remote sensing technology is crucial for identifying and monitoring abandoned cropland in large-scale areas.  However, limited information is available on the effective identification methods and spatial distribution patterns of abandoned cropland in the hilly and gully regions.  This study introduced two methods - the land-use trajectory and normalized difference vegetation index (NDVI) time series - for monitoring abandoned cropland and evaluating its spatial distribution in Yanhe River Basin using Landsat-8 images from 2019 to 2021.  The results showed that using a random forest algorithm, high-precision annual land-use classifications were achieved with the generation of reliable land-cover samples and an optimized feature dataset.  The overall accuracy (OA) and Kappa coefficient of the land-use maps exceeded 90% and 0.88, respectively, demonstrating the effectiveness of the classification over three years.  These two distinct change detection methods were used to identify abandoned cropland in the study area, and their accuracy and effectiveness were evaluated.  The land-use trajectory method performed better than the NDVI time series method for extracting abandoned cropland, with an OA of 83.5% and an F1 score of 84.7%.  According to the land-use trajectory detection results, the study area had 164.6 km2 of abandoned cropland area in 2021, with an abandonment rate of 16.3%.  Furthermore, cropland abandonment mainly occurred in the northwestern part of the region, which has harsh natural conditions, while abandonment was rare in the southern and eastern regions.  Topography and landforms significantly influenced the spatial distribution of abandoned cropland, with most abandoned cropland located in mountainous regions with higher elevations and steeper slopes.  The abandonment rate generally increased with the elevation and slope.  These findings provide valuable references and guidance for selecting appropriate methods to identify abandoned cropland and analyze its spatial distribution in the hilly and gully regions.  Our proposed methods offer robust solutions for monitoring abandoned cropland and optimizing land-use change detection in similar regions with complex landforms.

Key words: cropland abandonment ,  Landsat time series , land-use mapping , change detection , spatial distribution , hilly and gully regions