基于无人机和Landsat数据的近30年三江源地区土地退化动态监测
赵琳兴 , 王雁鹤 , 王子超 , 徐马强 , 李泽宇 , 祁昌贤 , 崔宝祖 , 王宗保
草业学报 ›› 2026, Vol. 35 ›› Issue (02) : 1 -14.
基于无人机和Landsat数据的近30年三江源地区土地退化动态监测
Dynamic monitoring of land degradation in the Three-River Headwaters Region over the past 30 years using unoccupied aerial vehicle imagery and Landsat data
土地退化严重威胁我国生态系统稳定与粮食安全。三江源地区作为西部重要的生态屏障,面临突出的土地退化问题,影响区域生态安全与社会经济发展。本研究基于实地采样、无人机与Landsat数据,随机森林(RF)、支持向量机(SVM)、分类和回归树模型(CART),构建多源数据的土地退化监测框架,监测近30年(1993、2003、2013、2023年)三江源地区土地退化动态,并分析其时空演变特征。结果表明:1)无人机与卫星数据结合使用可以明显提高退化识别精度,基于“光谱-植被指数-地形”特征的随机森林模型精度最优,土地沙化识别精度达94.73%,F1分数为95.85%,“黑土滩”型退化识别精度达90.98%,F1分数为95.18%。2)1993-2023年,未退化与“黑土滩”型退化面积先增后减,盐渍化面积呈波动变化,先增加后减少再增加,沙化面积持续减少,各类型面积稳定不变的面积占比超1/2。3)总体上,黑土滩和沙化等级呈减轻趋势,重度黑土滩与中度沙化面积明显减少;轻中度盐渍化变化较小,重度盐渍化面积下降。本研究可为生态脆弱区土地退化监测提供新思路,并为区域生态保护与可持续发展提供科学依据。
Land degradation is a critical ecological and environmental issue that threatens ecosystem stability and food security in China. As a key ecological barrier in western China, the Three-River Headwaters Region is undergoing severe land degradation, which presents significant challenges for regional ecological security and socioeconomic development. Based on field sampling, unoccupied aerial vehicle (UAV) imagery, and Landsat data, this study established a multi-source data framework for monitoring land degradation by employing random forest (RF), support vector machine (SVM), and classification and regression tree (CART) models. The framework was applied to monitor land degradation dynamics in the Three-River Headwaters Region over the past three decades (1993-2003, 2003-2013, and 2013-2023), and to analyze its spatiotemporal evolution patterns. The results indicate that: 1) The integration of UAV and satellite data significantly improved the accuracy of degraded land detection. Among the models tested in this study, the RF model based on spectral and vegetation indexes and topographic features achieved the highest accuracy. Specifically, the accuracy of identifying desertified land reached 94.73% with an F1-score of 95.85%, while the accuracy of detecting degraded black soil beach land reached 90.98% with an F1-score of 95.18%. 2) From 1993 to 2023, the areas of non-degraded land and degraded black soil beach land initially increased and then decreased. The area of salinized land showed a fluctuating trend-increasing initially, then decreasing, and increasing again, while the area of desertified land continuously declined. For all degradation types, more than half of the affected areas remained in a stable state throughout the monitoring period. 3) Overall, both the severity of black soil beach degradation and desertification showed a decreasing trend, with substantial reductions in the area of severely degraded black soil land moderately desertified land. In contrast, there were only small changes in the area of mildly and moderately salinized land, but a notable decrease in the area of severely salinized land.
| [1] |
Ren Q, He C Y, Huang Q X, et al. Impacts of urban expansion on natural habitats in global drylands. Nature Sustainability, 2022, 5(10): 869-878. |
| [2] |
Peng W Y, Li B J, Liu C. Xi Jinping’s important exposition on ecological security and the construction of ecological security system. Chinese Journal of Urban and Enviromental Studies, 2021(1): 20-34. |
| [3] |
彭文英, 李碧君, 刘灿. 习近平关于生态安全重要论述及生态安全体系建设研究. 城市与环境研究, 2021(1): 20-34. |
| [4] |
Chen Y N, Li Z Q, Xu J H, et al. Changes and protection suggestions in water resources and ecological environment in arid region of Northwest China. Bulletin of Chinese Academy of Sciences, 2023, 38(3): 385-393. |
| [5] |
陈亚宁, 李忠勤, 徐建华, 中国西北干旱区水资源与生态环境变化及保护建议. 中国科学院院刊, 2023, 38(3): 385-393. |
| [6] |
Food and Agriculture Organization of the United Nations. Land degradation. Rome: Food and Agriculture Organization of the United Nations, 1971. |
| [7] |
Chen A, Yang X C, Guo J, et al. Synthesized remote sensing-based desertification index reveals ecological restoration and its driving forces in the northern sand-prevention belt of China. Ecological Indicators, 2021, 131: 108230. |
| [8] |
Wang Z, Song D X, He T, et al. Developing spatial and temporal continuous fractional vegetation cover based on Landsat and Sentinel-2 data with a deep learning approach. Remote Sensing, 2023, 15(11): 2948. |
| [9] |
Zhong G R, Chen J J, Huang R J, et al. High spatial resolution fractional vegetation coverage inversion based on UAV and Sentinel-2 data: A case study of alpine grassland. Remote Sensing, 2023, 15(17): 4266. |
| [10] |
Gao X C. Research on rodent damage and degradation of desert grassland based on UAV hyperspectral remote sensing. Hohhot: Inner Mongolia Agricultural University, 2024. |
| [11] |
高新超. 基于无人机高光谱遥感的荒漠草原鼠害及退化研究. 呼和浩特: 内蒙古农业大学, 2024. |
| [12] |
Jin E E D M T. Research on identification and inversion of degradation indicator of desert grassland based on hyperspectral remote sensing by unmanned aerial vehicle. Hohhot: Inner Mongolia Agricultural University, 2024. |
| [13] |
金额尔都木吐. 基于无人机高光谱遥感的荒漠草原退化指示地物识别与反演研究. 呼和浩特: 内蒙古农业大学, 2024. |
| [14] |
Wang H J, Fan W J, Cui Y K, et al. Hyperspectral remote sensing monitoring of grassland degradation. Spectroscopy and Spectral Analysis, 2010, 30(10): 2734-2738. |
| [15] |
王焕炯, 范闻捷, 崔要奎, 草地退化的高光谱遥感监测方法. 光谱学与光谱分析, 2010, 30(10): 2734-2738. |
| [16] |
Liu X D, Liu R T, Liu A J, et al. Study on information extraction and the dynamic monitoring of grassland coverage in Three River Source area. Acta Agrestia Sinica, 2010, 18(2): 154-159. |
| [17] |
刘晓东, 刘荣堂, 刘爱军, 三江源地区草地覆盖遥感信息提取方法及动态研究. 草地学报, 2010, 18(2): 154-159. |
| [18] |
Li Y J, Zhang L. Sandy land monitoring method based on classification index model. Journal of Geo-information Science, 2021, 23(4): 680-691. |
| [19] |
李宇君, 张磊. 基于沙地指数模型的沙地监测方法. 地球信息科学学报, 2021, 23(4): 680-691. |
| [20] |
Zhang Q, Zhou H K, Wang X L, et al. Research on comprehensive definition and classification of degraded grassland of black soil beach cased on morphology-vegetation-soil characteristics. Qinghai Science and Technology, 2023, 30(5): 19-26. |
| [21] |
张强, 周华坤, 王晓丽, 基于形态-植被-土壤特征的黑土滩退化草地综合定义与分类方法研究. 青海科技, 2023, 30(5): 19-26. |
| [22] |
Chen G M. The status of the degraded pasture and its strategyes of management in black beach of the headwater region of the Three River. Journal of Grassland and Forage Science, 2005(10): 37-39, 44. |
| [23] |
陈国明. 三江源地区“黑土滩”退化草地现状及治理对策. 四川草原, 2005(10): 37-39, 44. |
| [24] |
Ma Y S, Lang B N, Wang Q J. Review and prospect of the study on ‘black soil type’ deteriorated grassland. Pratacultural Science, 1999(2): 5-9. |
| [25] |
马玉寿, 郎百宁, 王启基. “黑土型”退化草地研究工作的回顾与展望. 草业科学, 1999(2): 5-9. |
| [26] |
Dang X P, Dong Y. Study on the dynamic changes of desertification land in the Three Rivers Source region of Qinghai Province. Inner Mongolia Forestry Investigation and Design, 2017, 40(6): 20-26. |
| [27] |
党晓鹏, 东雨. 青海省三江源地区沙化土地变化动态研究. 内蒙古林业调查设计, 2017, 40(6): 20-26. |
| [28] |
Shang Z H, Long R J. Formation reason and recovering problem of the‘black soil type’degraded alpine grassland in Qinghai Tibetan Plateau. Chinese Journal of Ecology, 2005(6): 652-656. |
| [29] |
尚占环, 龙瑞军. 青藏高原“黑土型”退化草地成因与恢复. 生态学杂志, 2005(6): 652-656. |
| [30] |
Shang Z H, Dong Q M, Shi J J, et al. Research progress in recent ten years of ecological restoration for “black soil land” degraded grassland on Tibetan Plateau-Concurrently discuss of ecological restoration in Sanjiangyuan region. Acta Agrestia Sinica, 2018, 26(1): 1-21. |
| [31] |
尚占环, 董全民, 施建军, 青藏高原“黑土滩”退化草地及其生态恢复近10年研究进展——兼论三江源生态恢复问题. 草地学报, 2018, 26(1): 1-21. |
| [32] |
Yu Z R, Wang J W. Land salinization in China and the prevention countermeasures. Rural Eco-Environment, 1997, 13(3): 2-6. |
| [33] |
宇振荣, 王建武. 中国土地盐碱化及其防治对策研究. 农村生态环境, 1997, 13(3): 2-6. |
| [34] |
Ma H W, Wang Y F, Guo E L. Remote sensing monitoring of aeolian desertification in Ongniud Banner based on GEE. Arid Zone Research, 2023, 40(3): 504-516. |
| [35] |
马浩文, 王永芳, 郭恩亮. 基于GEE的翁牛特旗土地沙漠化遥感监测. 干旱区研究, 2023, 40(3): 504-516. |
| [36] |
Xia L, Song X N, Cai S H, et al. Role of surface hydrothermal elements in grassland degradation over the Tibetan Plateau. Acta Ecologica Sinica, 2021, 41(11): 4618-4631. |
| [37] |
夏龙, 宋小宁, 蔡硕豪, 地表水热要素在青藏高原草地退化中的作用. 生态学报, 2021, 41(11): 4618-4631. |
| [38] |
He H X, Yan J N, Liang D, et al. Time-series land cover change detection using deep learning-based temporal semantic segmentation. Remote Sensing of Environment, 2024, 305: 114101. |
| [39] |
Li Z M, Chen B, Wu S B, et al. Deep learning for urban land use category classification: A review and experimental assessment. Remote Sensing of Environment, 2024, 311: 114290. |
| [40] |
Gao G Y, Liang Y, Liu J B, et al. A modified RUSLE model to simulate soil erosion under different ecological restoration types in the loess hilly area. International Soil and Water Conservation Research, 2024, 12(2): 258-266. |
| [41] |
Qiu H H, Hu B Q, Zhang Z. Impacts of land use change on ecosystem service value based on SDGs report-Taking Guangxi as an example. Ecological Indicators, 2021, 133: 108366. |
| [42] |
Misuk K, KyuBaek H. An empirical evaluation of sampling methods for the classification of imbalanced data. PLoS One, 2022, 17(7): e0271260. |
| [43] |
Millard K, Richardson M. On the importance of training data sample selection in random forest image classification: A case study in peatland ecosystem mapping. Remote Sensing, 2015, 7(7): 8489-8515. |
| [44] |
Wang F, Ding J L, Wu M C. Remote sensing monitoring models of soil salinization based on NDVI-SI feature space. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(8): 168-173, 8. |
| [45] |
王飞, 丁建丽, 伍漫春. 基于NDVI-SI特征空间的土壤盐渍化遥感模型. 农业工程学报, 2010, 26(8): 168-173, 8. |
| [46] |
Breiman L. Bagging predictors. Machine Learning, 1996, 24: 123-140. |
| [47] |
Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995, 20: 273-297. |
| [48] |
Breiman L, Friedman J, Olshen R A, et al. Classification and regression trees. Routledge, 2017.https://doi.org/10.1201/9781315139470. |
| [49] |
National Technical Committee on Desertification Control Standardization (SAC/TC 365). Specification for types and classification of land degradation: LY/T 3354-2023. Beijing: China Standards Press, 2023. |
| [50] |
全国荒漠化防治标准化技术委员会(SAC/TC 365). 土地退化类型与分级规范: LY/T 3354-2023. 北京: 中国标准出版社, 2023. |
| [51] |
Liu K Y, Zhao Z Y, Li L. Research progress in the application of SAR data in soil salinity monitoring. Journal of Geo-information Science, 2024, 26(8): 1893-1910. |
| [52] |
刘康怡, 赵振宇, 李俐. SAR数据在土壤盐渍化监测中的应用研究进展.地球信息科学学报, 2024, 26(8): 1893-1910. |
| [53] |
Chen A, Xu C, Zhang M, et al. Cross-scale mapping of above-ground biomass and shrub dominance by integrating UAV and satellite data in temperate grassland. Remote Sensing of Environment, 2024, 304: 114024. |
| [54] |
Li W K, Zhao Q H, Jia S H, et al. Multi-feature and multi-level Sentinel-2 image extraction of lake and reservoir water bodies on Liaoning Province. Bulletin of Surveying and Mapping, 2024(3): 37-42, 106. |
| [55] |
李文康, 赵泉华, 贾淑涵, 多特征多层次Sentinel-2影像辽宁省湖库水体提取. 测绘通报, 2024(3): 37-42, 106. |
中国地质调查局项目(DD20243409)
/
| 〈 |
|
〉 |