A Novel Framework for Spatiotemporal Susceptibility Prediction of Rainfall-Induced Landslides: A Case Study in Western Pennsylvania

被引:0
作者
Xiong, Jun [1 ]
Pei, Te [2 ]
Qiu, Tong [3 ]
机构
[1] Penn State Univ, Dept Civil & Environm Engn, University Pk, PA 16802 USA
[2] CUNY City Coll, Dept Civil Engn, New York, NY 10031 USA
[3] Univ Utah, Dept Civil & Environm Engn, Salt Lake City, UT 84112 USA
关键词
landslides; landslide susceptibility mapping; machine learning; rainfall; spatiotemporal prediction; LOGISTIC-REGRESSION; NEURAL-NETWORKS; THRESHOLDS; PROBABILITY; INITIATION; RATIO; MAPS;
D O I
10.3390/rs16183526
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Landslide susceptibility measures the probability of landslides occurring under certain geo-environmental conditions and is essential in landslide hazard assessment. Landslide susceptibility mapping (LSM) using data-driven methods applies statistical models and geospatial data to show the relative propensity of slope failure in a given area. However, due to the rarity of multi-temporal landslide inventory, conventional data-driven LSMs are primarily generated by spatial causative factors, while the temporal factors remain limited. In this study, a spatiotemporal LSM is carried out using machine learning (ML) techniques to assess rainfall-induced landslide susceptibility. To achieve this, two landslide inventories are collected for southwestern Pennsylvania: a spatial inventory and a multi-temporal inventory, with 4543 and 223 historical landslide samples, respectively. The spatial inventory lacks the information to describe landslide temporal distribution; there are insufficient samples in the temporal inventory to represent landslide spatial distribution. A novel paradigm of data augmentation through non-landslide sampling based on domain knowledge is applied to leverage both spatial and temporal information for ML modeling. The results show that the spatiotemporal ML model using the proposed data augmentation predicts well rainfall-induced landslides in space and time across the study area, with a value of 0.86 of the area under the receiver operating characteristic curve (AUC), which makes it an effective tool in rainfall-induced landslide hazard mitigation and forecasting.
引用
收藏
页数:20
相关论文
共 50 条
  • [11] Delano H.L., 2001, Educational Series, V9
  • [12] Rainfall thresholds for the initiation of landslides in central and southern Europe
    Guzzetti, F.
    Peruccacci, S.
    Rossi, M.
    Stark, C. P.
    [J]. METEOROLOGY AND ATMOSPHERIC PHYSICS, 2007, 98 (3-4) : 239 - 267
  • [13] Uncertainties of landslide susceptibility prediction: influences of different study area scales and mapping unit scales
    Huang, Faming
    Cao, Yu
    Li, Wenbin
    Catani, Filippo
    Song, Guquan
    Huang, Jinsong
    Yu, Changshi
    [J]. INTERNATIONAL JOURNAL OF COAL SCIENCE & TECHNOLOGY, 2024, 11 (01)
  • [14] Regional rainfall-induced landslide hazard warning based on landslide susceptibility mapping and a critical rainfall threshold
    Huang, Faming
    Chen, Jiawu
    Liu, Weiping
    Huang, Jinsong
    Hong, Haoyuan
    Chen, Wei
    [J]. GEOMORPHOLOGY, 2022, 408
  • [15] Review on landslide susceptibility mapping using support vector machines
    Huang, Yu
    Zhao, Lu
    [J]. CATENA, 2018, 165 : 520 - 529
  • [16] Kavzoglu T, 2019, ADV NAT TECH HAZ RES, V50, P283, DOI 10.1007/978-3-319-77377-3_13
  • [17] Monitoring and prediction of landslide-related deformation based on the GCN-LSTM algorithm and SAR imagery
    Khalili, Mohammad Amin
    Guerriero, Luigi
    Pouralizadeh, Mostafa
    Calcaterra, Domenico
    Di Martire, Diego
    [J]. NATURAL HAZARDS, 2023, 119 (01) : 39 - 68
  • [18] Effect of antecedent rainfall conditions and their variations on shallow landslide-triggering rainfall thresholds in South Korea
    Kim, Suk Woo
    Chun, Kun Woo
    Kim, Minseok
    Catani, Filippo
    Choi, Byoungkoo
    Seo, Jung Il
    [J]. LANDSLIDES, 2021, 18 (02) : 569 - 582
  • [19] Spatial and temporal analysis of a global landslide catalog
    Kirschbaum, Dalia
    Stanley, Thomas
    Zhou, Yaping
    [J]. GEOMORPHOLOGY, 2015, 249 : 4 - 15
  • [20] A global landslide catalog for hazard applications: method, results, and limitations
    Kirschbaum, Dalia Bach
    Adler, Robert
    Hong, Yang
    Hill, Stephanie
    Lerner-Lam, Arthur
    [J]. NATURAL HAZARDS, 2010, 52 (03) : 561 - 575