Machine learning-based monitoring of mangrove ecosystem dynamics in the Indus Delta

被引:0
|
作者
Zhou, Ying [1 ]
Dai, Zhijun [1 ,2 ]
Liang, Xixing [1 ,3 ]
Cheng, Jinping [4 ]
机构
[1] East China Normal Univ, State Key Lab Estuarine & Coastal Res, Shanghai 200062, Peoples R China
[2] Qingdao Marine Sci & Technol Ctr, Lab Marine Geol, Qingdao 266061, Peoples R China
[3] Beibu Gulf Univ Qinzhou, Guangxi Key Lab Marine Environm Change & Disaster, Qinzhou 200062, Peoples R China
[4] Educ Univ Hong Kong, Dept Sci & Environm Studies, Hong Kong, Peoples R China
关键词
Mangrove expansion; Hydro-sediment dynamic; Machine Learning; Random Forest; Tidal channel; Shoreline erosion; SEA-LEVEL RISE; RANDOM FOREST; CLIMATE-CHANGE; RIVER DELTA; CLASSIFICATION; EXTENT; RECOMMENDATIONS; VULNERABILITY; ADAPTATION; SATELLITE;
D O I
10.1016/j.foreco.2024.122231
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Mangrove forests play a vital role in carbon sequestration, typhoon-induced wave attenuation, and the provision of ecological services. However, mangrove ecosystems have experienced large-scale loss globally due to rising sea levels and anthropogenic activities. This study investigates the dynamic changes in mangrove cover within the mega-Indus delta, the largest delta in Pakistan and Southern Asia, using multi-temporal remote sensing data and machine learning techniques from 1988 to 2023. The results indicate an increasing trend in mangrove areas in the Indus Delta, with an average annual growth rate of 18.72 %. The spatial distribution of mangrove forests tends to concentrate towards the landward areas, extending along tidal channels, while losses primarily occur in the seaward regions. Rising sea levels pose a potential threat to the survival of these mangroves. The strong southwest monsoon-driven waves are the leading cause of shoreline erosion of the Indus Delta mangroves. Meanwhile, the reduction in riverine sediment discharge is not associated with the increase in mangrove area. Instead, the tidal currents influenced by the southwest monsoon carry sediments into the delta's tidal channels, causing them to fill and create suitable habitats for mangroves, which are the primary drivers of the observed mangrove expansion in the Indus Delta. Additionally, afforestation activities observed in the northwest and southwest parts of the study area have contributed to the restoration of mangroves. The loss of mangroves in the northernmost part of the northwest region was attributed to an oil spill incident. This study highlights the dynamic nature of mangrove ecosystems in the Indus Delta, characterized by an arid climate and low population density. The findings provide valuable insights into the factors influencing mangrove gain and loss and can inform management strategies for global mangrove restoration efforts.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] Machine Learning-based Cybersecurity Defence of Wide-area Monitoring Systems
    He, Qian
    Bai, Feifei
    Cui, Yi
    Zillmann, Matthew
    2022 IEEE/IAS INDUSTRIAL AND COMMERCIAL POWER SYSTEM ASIA (I&CPS ASIA 2022), 2022, : 991 - 996
  • [42] Machine learning-based monitoring method for the electricity consumption of a healthcare facility in Italy
    Zini, Marco
    Carcasci, Carlo
    ENERGY, 2023, 262
  • [43] Machine learning-based precise monitoring of aluminium-magnesium alloy dust
    Zhao, Fengyu
    Gao, Wei
    Lu, Jianxin
    Jiang, Haipeng
    JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES, 2024, 92
  • [44] A review on application of machine learning-based methods for power system inertia monitoring
    Heidari, Mahdi
    Ding, Lei
    Kheshti, Mostafa
    Bao, Weiyu
    Zhao, Xiaowei
    Popov, Marjan
    Terzija, Vladimir
    INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2024, 162
  • [45] A Machine Learning-Based Damage Estimation Model for Monitoring Reinforced Concrete Structures
    Inderyas, Omair
    Tayfur, Sena
    Alver, Ninel
    Catbas, F. Necati
    DATA SCIENCE IN ENGINEERING, VOL. 10, IMAC 2024, 2025, : 109 - 115
  • [46] Data Augmentation Applied to Machine Learning-Based Monitoring of a Pulp and Paper Process
    Parente, Andrea Pereira
    de Souza Jr, Mauricio Bezerra
    Valdman, Andrea
    Mattos Folly, Rossana Odette
    PROCESSES, 2019, 7 (12)
  • [47] Machine learning-based modeling of surface water temperature dynamics in arctic lakes
    Kim, Hyung Il
    Kim, Dongkyun
    Salamattalab, Mohammad Milad
    Mahdian, Mehran
    Bateni, Sayed M.
    Noori, Roohollah
    Environmental Science and Pollution Research, 2024, 31 (49) : 59642 - 59655
  • [48] Environmental chemical exposure dynamics and machine learning-based prediction of diabetes mellitus
    Wei, Hongcheng
    Sun, Jie
    Shan, Wenqi
    Xiao, Wenwen
    Wang, Bingqian
    Ma, Xuan
    Hu, Weiyue
    Wang, Xinru
    Xia, Yankai
    SCIENCE OF THE TOTAL ENVIRONMENT, 2022, 806
  • [49] Machine Learning-Based Prediction of Ecosystem-Scale CO2 Flux Measurements
    Uyekawa, Jeffrey
    Leland, John
    Bergl, Darby
    Liu, Yujie
    Richardson, Andrew D.
    Lucas, Benjamin
    LAND, 2025, 14 (01)
  • [50] Satellite-based assessment of the extent and changes in the mangrove ecosystem of the Niger Delta
    James, Godstime K.
    Adegoke, Jimmy O.
    Saba, Ekechukwu
    Nwilo, Peter
    Akinyede, Joseph
    MARINE GEODESY, 2007, 30 (03) : 249 - 267