Decadal Dynamics of Rangeland Cover Using Remote Sensing and Machine Learning Approach

被引：1

作者：

Yang, Yujing ^{[1
]}

Li, Zhiming ^{[1
]}

Quddoos, Abdul ^{[2
,3
]}

Aslam, Rana Waqar ^{[2
]}

Naz, Iram ^{[2
]}

Khalid, Muhammad Burhan ^{[4
]}

Afzal, Zohaib ^{[2
]}

Liaquat, Muhammad Azeem ^{[5
]}

Abdullah-Al-Wadud, M. ^{[6
]}

机构：

[1] Southwest Petr Univ, Sch Civil Engn & Geomat, Nanchong 637001, Sichuan, Peoples R China

[2] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China

[3] Environm Protect Agcy Punjab, Lahore 54000, Pakistan

[4] Nanjing Univ Informat Sci & Technol, Dept Atmospher Remote Sensing & Atmospher Sounding, Nanjing 210044, Peoples R China

[5] Univ Punjab, Dept Space Sci, Lahore 54000, Pakistan

[6] King Saud Univ, Coll Comp & Informat Sci, Dept Software Engn, Riyadh 11543, Saudi Arabia

来源：

RANGELAND ECOLOGY & MANAGEMENT | 2025年 / 100卷

关键词：

Rangeland degradation; Remote Sensing; Machine learning; ecological city construction; Land cover change; CLIMATE-CHANGE; VEGETATION; ADAPTATION; NORTH;

D O I：

10.1016/j.rama.2025.02.002

中图分类号：

Q14 [生态学（生物生态学）];

学科分类号：

071012 ; 0713 ;

摘要：

Rangeland degradation in arid and semi-arid regions poses significant environmental and socioeconomic challenges globally. This study aims to assess the Spatio-temporal dynamics of rangeland changes in Khushab district, Pakistan, between 20 0 0 and 2020 by developing an integrated approach combining remote sensing, vegetation indices, and machine learning techniques. The specific objectives were to: (1) quantify rangeland extent changes using multi-temporal Landsat imagery, (2) evaluate rangeland health through multiple vegetation indices, and (3) analyze the primary drivers of rangeland transformation. The methodology integrated Landsat-derived land use land cover (LULC) classification using Random Forest and SMILE CART algorithms, analysis of six vegetation indices (NDVI, GNDVI, SAVI, EVI, ARVI), and land surface temperature (LST) assessment. The classification accuracy exceeded 90% for Random Forest and 87% for SMILE CART across all time periods. Results revealed significant rangeland degradation, with area declining from 9% to 6% of total land between 20 0 0 and 2020. Cropland expansion was the primary driver, increasing from 16% to 29% and converting 218 sq km of rangeland. Vegetation indices showed stable NDVI but declining GNDVI maximums from 0.37 to 0.36, indicating deteriorating plant health. Rising minimum LST from 27.82 degrees C to 31.81 degrees C suggested increasing heat stress on vegetation. This research demonstrates the effectiveness of integrating multiple remote sensing approaches with machine learning for comprehensive rangeland monitoring. The findings provide crucial baseline data for evidence- based policy making and sustainable rangeland management in Pakistan's semi-arid regions. Future work should incorporate ground validation and socioeconomic surveys to better understand degradation drivers and develop targeted conservation strategies. (c) 2025 The Society for Range Management. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

引用

页码：1 / 13

页数：13

共 76 条

[21] Duan C., Shi P., Zong N., Zhang X., Yu C., Assessing rangeland sensitivity to degradation in North Tibet, Rangel. Ecol. Manag., 84, pp. 86-97, (2022)
[22] Duarte-Guardia S., Peri P.L., Martinez-Pastur G., Lasagno R., Lencinas M.V., Thomas E., Ladd B., Value of biodiversity on Patagonian rangeland: estimation via a hedonic price index, Rangel. Ecol. Manag., 92, pp. 122-128, (2024)
[23] Feng L., Hussain S., Pricope N.G., Arshad S., Tariq A., Feng L., Mubeen M., Aslam R.W., Fnais M.S., Li W., El-Askary H., Seasonal dynamics in land surface temperature in response to land use land cover changes using Google Earth engine, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 17, pp. 17983-17997, (2024)
[24] Feng L., Naz I., Quddoos A., Zafar Z., Gan M., Aslam M., Hussain Z.K., Soufan W., Almutairi K.F., Exploring rangeland dynamics in Punjab, Pakistan: integrating LULC, LST, and remote sensing for ecosystem analysis (2000–2020), Rangel. Ecol. Manag, 98, pp. 377-388, (2024)
[25] Gang C., Zhou W., Chen Y., Wang Z., Sun Z., Li J., Qi J., Odeh I., Quantitative assessment of the contributions of climate change and human activities on global grassland degradation, Environ. Earth Sci., 72, pp. 4273-4282, (2014)
[26] Gitelson A.A., Kaufman Y.J., Merzlyak M.N., Use of a green channel in remote sensing of global vegetation from EOS-MODIS, Remote Sens. Environ., 58, pp. 289-298, (1996)
[27] Gitelson A.A., Merzlyak M.N., Remote sensing of chlorophyll concentration in higher plant leaves, Adv. Sp. Res., 22, pp. 689-692, (1998)
[28] Gulshad K., Szydlowski M., Yaseen A., Aslam R.W., A comparative analysis of methods and tools for low impact development (LID) site selection, J. Environ. Manage., 354, (2024)
[29] Hao Z., Haseeb M., Xiangtian Z., Tahir Z., Mahmood S.A., Tariq A., Aslam R.W., Abdullah-Al-Wadud M., El-Askary H.M., Multitemporal analysis of urbanization-driven slope and ecological impact using machine-learning and remote sensing techniques, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 18, pp. 1876-1895, (2025)
[30] Herve-Fernandez P., Munoz-Arriagada R., Glucevic-Almonacid C., Bahamonde-Vidal L., Radic-Schilling S., Influence of Rangeland land cover on infiltration rates, field-saturated hydraulic conductivity, and soil water repellency in Southern Patagonia, Rangel. Ecol. Manag., 90, pp. 92-100, (2023)

← 1 2 3 4 5 6 7 8 →