Random forest-based analysis of land cover/land use LCLU dynamics associated with meteorological droughts in the desert ecosystem of Pakistan

被引:8
作者
Faheem, Zulqadar [1 ]
Kazmi, Jamil Hasan [1 ]
Shaikh, Saima [1 ]
Arshad, Sana [2 ]
Mohammed, Safwan [3 ,4 ]
机构
[1] Univ Karachi, Dept Geog, Karachi 75270, Pakistan
[2] Islamia Univ Bahawalpur, Dept Geog, Bahawalpur 63100, Pakistan
[3] Univ Debrecen, Inst Land Use Tech & Prec Technol, Fac Agr & Food Sci & Environm Management, H-4032 Debrecen, Hungary
[4] Univ Debrecen, Inst Agr Res & Educ Farm, Boszormeny 138, H-4032 Debrecen, Hungary
关键词
Change Detection; Climate Change; SPI; Development; Arid ecosystem; CLIMATE-CHANGE; USE/LAND COVER; LOESS PLATEAU; CLASSIFICATION; VEGETATION; DESERTIFICATION; IMPACTS; INDEXES; IMAGE; GRAIN;
D O I
10.1016/j.ecolind.2024.111670
中图分类号
X176 [生物多样性保护];
学科分类号
090705 ;
摘要
Dry land ecosystems extend over 40 % of the Earth, supporting an estimated 3 billion human population. Thus, quantifying LCLU changes in such ecosystems is essential for achieving sustainable development goals. In this context, this research aimed to examine the LCLU changes in the past three decades (1990 - 2020) in an arid ecosystem of Pakistan, i.e., the Cholisatn desert. Three remote sensing indices, the normalized difference vegetation index (NDVI), normalized difference barren index (NDBaI), and top grain soil index (TGSI) are taken as LCLU representatives to examine their temporal relationship associated with meteorological drought, e.g. the standardized precipitation index (SPI). Moreover, machine learning-based random forest (RF) classification followed by change detection techniques was implemented. Results from RF classifier revealed the applicability of RF in accurately predicting LULC with validation overall accuracy of 0.99. Output of the research revealed an interesting finding where the desert experienced significant LCLU change over the last three decades. The highest vegetation expansion (4.4 %) took place from 2014 to 2020 at the expense of the highest reduction of barren land (-6.3 %). Mann-Kendall trend (MK) and Sen's slope (SS) analysis showed a significant (P < 0.001) increasing trend of NDVI (SS = 0.004), SPI (SS = 0.01 and 0.04) and decreasing trend of NDBaI and TGSI (SS = -0.001, -0.005). Interestingly, the significant positive Pearson correlation range (r = 0.6-0.8) of NDVI with SPI-1 to 6, and negative correlation range (r = 0.5-0.7) of NDBaI with SPI indices reveals a strong linear relationship between LCLU and meteorological drought. The research provides substantial implications for policy makers and stakeholders emphasizing the need for proactive strategies such as drought resistant vegetation to improve and maintain the ecological health of desert and combating the negative impacts of climatic change.
引用
收藏
页数:20
相关论文
共 116 条
  • [1] DETERMINATION OF FORAGE PRODUCTIVITY, CARRYING CAPACITY AND PALATABILITY OF BROWSE VEGETATION IN ARID RANGELANDS OF CHOLISTAN DESERT (PAKISTAN)
    Abdullah, M.
    Rafay, M.
    Sial, N.
    Rasheed, F.
    Nawaz, M. F.
    Nouman, W.
    Ahmad, I
    Ruby, T.
    Khalil, S.
    [J]. APPLIED ECOLOGY AND ENVIRONMENTAL RESEARCH, 2017, 15 (04): : 623 - 637
  • [2] The impacts of land use and land cover change on biophysical processes in West Africa using a regional climate model experimental approach
    Achugbu, Ifeanyi Chukwudi
    Laux, Patrick
    Olufayo, Ayo Akinlabi
    Balogun, Ifeoluwa Adebowale
    Dudhia, Jimy
    Arnault, Joel
    Gbode, Imoleayo E.
    Naabil, Edward
    Kunstmann, Harald
    [J]. INTERNATIONAL JOURNAL OF CLIMATOLOGY, 2023, 43 (04) : 1731 - 1755
  • [3] Climate change in rural Pakistan: evidence and experiences from a people-centered perspective
    Ajani, Amber
    van der Geest, Kees
    [J]. SUSTAINABILITY SCIENCE, 2021, 16 (06) : 1999 - 2011
  • [4] Akram M, 2008, Future of Drylands, P483
  • [5] Al-Quraishi AMF., 2020, ENV REMOTE SENSING G, DOI [10.1007/978-3-030-21344-2_15, DOI 10.1007/978-3-030-21344-2_15]
  • [6] Transfer Learning Models for Land Cover and Land Use Classification in Remote Sensing Image
    Alem, Abebaw
    Kumar, Shailender
    [J]. APPLIED ARTIFICIAL INTELLIGENCE, 2022, 36 (01)
  • [7] Monitoring the impacts of spatio-temporal land-use changes on the regional climate of city Faisalabad, Pakistan
    Arshad, Arfan
    Zhang, Wanchang
    Zaman, Muhammad Awais
    Dilawar, Adil
    Sajid, Zulqarnain
    [J]. ANNALS OF GIS, 2019, 25 (01) : 57 - 70
  • [8] Performance evaluation of ERA-5, JRA-55, MERRA-2, and CFS-2 reanalysis datasets, over diverse climate regions of Pakistan
    Arshad, Muhammad
    Ma, Xieyao
    Yin, Jun
    Ullah, Waheed
    Liu, Mengyang
    Ullah, Irfan
    [J]. WEATHER AND CLIMATE EXTREMES, 2021, 33
  • [9] Exploring dynamic response of agrometeorological droughts towards winter wheat yield loss risk using machine learning approach at a regional scale in Pakistan
    Arshad, Sana
    Kazmi, Jamil Hasan
    Prodhan, Foyez Ahmed
    Mohammed, Safwan
    [J]. FIELD CROPS RESEARCH, 2023, 302
  • [10] Geospatial assessment of early summer heatwaves, droughts, and their relationship with vegetation and soil moisture in the arid region of Southern Punjab, Pakistan
    Arshad, Sana
    Kazmib, Jamil Hasan
    Shaikhb, Saima
    Fatima, Munazza
    Faheema, Zulqadar
    Asifa, Muhammad
    Arshada, Waqar
    [J]. JOURNAL OF WATER AND CLIMATE CHANGE, 2022, 13 (11) : 4105 - 4129