Mitigating coastal flood risks in the Sundarbans: A combined InVEST and machine learning approach

被引:0
|
作者
Mondal, Ismail [1 ]
Mishra, Vahnishikha [1 ]
Hossain, S. K. Ariful [2 ,3 ]
Altuwaijri, Hamad Ahmed [4 ]
Juliev, Mukhiddin [5 ,6 ,7 ]
De, Amlan [8 ]
机构
[1] Univ Calcutta, Dept Marine Sci, Kolkata 700019, India
[2] CSIR, Natl Inst Oceanog, Goa 403004, India
[3] Jadavpur Univ, Sch Oceanog Studies, Kolkata 700032, India
[4] King Saud Univ, Coll Humanities & Social Sci, Dept Geog, Riyadh 1145, Saudi Arabia
[5] TIIAME Natl Res Univ, Inst Fundamental & Appl Res, Kori Niyoziy 39, Tashkent 100000, Uzbekistan
[6] Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Key Lab Ecol Safety & Sustainable Dev Arid Lands, Urumqi 830011, Peoples R China
[7] Turin Polytech Univ Tashkent, Dept Civil Engn & Architecture, Little Ring Rd St 17, Tashkent 100095, Uzbekistan
[8] Univ Calcutta, Inst Radio Phys & Elect, Kolkata 700009, West Bengal, India
关键词
Flood volume; Run-off retention volume; InVEST model; Sundarbans; Coastal flood risk mitigation; Machine learning; UN SDG; PRECIPITATION; MODEL; CLIMATOLOGY; CHARACTER; SURGES; BENGAL; GIS;
D O I
10.1016/j.pce.2025.103855
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Adjacent marine, terrestrial, and climatic systems and their dynamic interactions impact the complex estuarine and coastal processes in the West Bengal portion of the Ganges, Brahmaputra, and Meghna (GBM), known as the Sundarbans delta. Human expansion has designed the coastal sea, ponds, marshes, and estuary islands in this region to withstand the negative effects of societal, economic, recreational, and residential activities. Environmental factors such as increasing sea levels and climate change are significant sources of concern in this sensitive area. In recent decades, coastal flooding has emerged as a worldwide issue. Consequently, communities must prioritize the mitigation of flood risks. We use the InVEST and coastal flood risk mitigation (CFRM) model for the Sundarban deltaic region to analyze flood conditions caused by successive rainfalls of varying intensities and identify potential mitigating solutions. Increasing sea levels and global warming are endangering coastal regions to an escalating degree. Ongoing erosion and cyclones, which often deliver substantial rainfall, endanger human life and property, especially along low-lying deltaic coastlines. The Sundarbans and its mangrove ecosystems along India's east coast are vulnerable to tropical super-cyclones, and their resistance has diminished in recent decades owing to several adverse environmental stresses, including changing climate conditions. This study used the InVEST-CFRM model to evaluate the vulnerability of the Sundarbans' mangrove-fringed coastline in relation to flood volume and runoff attenuation index. We used the InVEST-CFRM model to assess the vulnerability of the intricate Indian Sundarbans. The study used machine learning (ML) methods to validate and predict the model, achieving a high accuracy value ranging from 0.76 to 0.99. The results demonstrate a steady increase in flooding along the deltaic coast of the Sundarbans in recent decades. The central regions of the Sundarbans are least vulnerable to flooding, but human settlements in these areas are most at risk. This research will provide effective mitigation techniques for restoring a sustainable environment and assist in identifying locations that are vulnerable to flooding and associated socioeconomic impacts.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Advancing flood damage modeling for coastal Alabama residential properties: A multivariable machine learning approach
    Museru, Mujungu Lawrence
    Nazari, Rouzbeh
    Giglou, Abolfazl N.
    Opare, Kofi
    Karimi, Maryam
    SCIENCE OF THE TOTAL ENVIRONMENT, 2024, 907
  • [2] Habitat quality and degradation change analysis for the Sundarbans mangrove forest using invest habitat quality model and machine learning
    Mondal, Ismail
    Naskar, Pijush Kanti
    Alsulamy, Saleh
    Jose, Felix
    Hossain, SK. Ariful
    Mohammad, Lal
    De, Tarun Kumar
    Khedher, Khaled Mohamed
    Salem, Mohamed Abdelaziz
    Benzougagh, Brahim
    Juliev, Mukhiddin
    ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY, 2024,
  • [3] Garbage In, Garbage Out: Mitigating the Ethical Risks of Artificial Intelligence and Machine Learning
    Stall, S.
    TOXICOLOGY LETTERS, 2024, 399 : S49 - S49
  • [4] A machine learning approach to evaluate coastal risks related to extreme weather events in the Veneto region (Italy)
    Dal Barco, Maria Katherina
    Maraschini, Margherita
    Ferrario, Davide Mauro
    Nguyen, Ngoc Diep
    Torresan, Silvia
    Vascon, Sebastiano
    Critto, Andrea
    INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION, 2024, 108
  • [5] Mitigating Blackouts via Smart Relays: A Machine Learning Approach
    Zhang, Yi
    Ilic, Marija D.
    Tonguz, Ozan K.
    PROCEEDINGS OF THE IEEE, 2011, 99 (01) : 94 - 118
  • [6] Mitigating the Multicollinearity Problem and Its Machine Learning Approach: A Review
    Chan, Jireh Yi-Le
    Leow, Steven Mun Hong
    Bea, Khean Thye
    Cheng, Wai Khuen
    Phoong, Seuk Wai
    Hong, Zeng-Wei
    Chen, Yen-Lin
    MATHEMATICS, 2022, 10 (08)
  • [7] Assessing Surface Water Flood Risks in Urban Areas Using Machine Learning
    Li, Zhufeng
    Liu, Haixing
    Luo, Chunbo
    Fu, Guangtao
    WATER, 2021, 13 (24)
  • [8] Assessing climate risks from satellite imagery with machine learning: A case study of flood risks in Jakarta
    Yang, Jeasurk
    Ahn, Donghyun
    Bahk, Junbeom
    Park, Sungwon
    Rizqihandari, Nurrokhmah
    Cha, Meeyoung
    CLIMATE RISK MANAGEMENT, 2024, 46
  • [9] Use of machine learning algorithms to assess flood susceptibility in the coastal area of Bangladesh
    Hasan, Md. Hasibul
    Ahmed, Asib
    Nafee, K. M.
    Hossen, Amzed
    OCEAN & COASTAL MANAGEMENT, 2023, 236
  • [10] A Hybrid Machine Learning Approach for Flood Risk Assessment and Classification
    Inyang, Udoinyang Godwin
    Akpan, Emem Etok
    Akinyokun, Oluwole Charles
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2020, 19 (02)