Prediction of Coseismic Landslides by Explainable Machine Learning Methods

The MJMA 7.6 (Mw 7.5) Noto Peninsula Earthquake of 1 January 2024 in Japan triggered widespread slope failures across northern Noto region, but their spatial controls and susceptibility patterns remain poorly quantified. Most previous studies have focused mainly on fault rupture, ground deformation, and tsunami impacts, leaving a clear gap in machine learning based assessment of earthquake-induced slope failures. This study integrates 2323 mapped landslides with eleven conditioning factors to develop the first data-driven susceptibility framework for the 2024 event. Spatial analysis shows that 75% of the landslides are smaller than 3220 m2 and nearly half occurred within about 23 km of the epicenter, reflecting concentrated ground shaking beyond the rupture zone. Terrain variables such as slope (mean 31.8°), southwest-facing aspects, and elevations of 100–300 m influenced the failure patterns, along with peak ground acceleration values of 0.8–1.1 g and proximity to roads and rivers. Six supervised machine learning models were trained, with Random Forest and Gradient Boosting achieving the highest accuracies (AUC = 0.95 and 0.94, respectively). Explainable AI using SHapley Additive exPlanations (SHAP) identified slope, epicentral distance, and peak ground acceleration as the dominant predictors. The resulting susceptibility maps align well with observed failures and provide an interpretable foundation for post-earthquake hazard assessment and regional risk reduction. Further work should integrate post-seismic rainfall, multi-temporal inventories, and InSAR deformation to support dynamic hazard assessment and improved early warning.

• Publication year

  2026

• Venue

  GeoHazards

• Publication date

  2026-01-02

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3390/geohazards7010007
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Application of LiDAR Differentiation and a Modified Savage–Hutter Model to Analyze Co-Seismic Landslides: A Case Study of the 2024 Noto Earthquake, Japan

  2025cited by this paper
• Machine Learning Ensemble Methods for Co-Seismic Landslide Susceptibility: Insights from the 2015 Nepal Earthquake

  2025influential reference
• Characteristics and controlling factors of landslides triggered by the 2024 Noto Peninsula Earthquake

  2025cited by this paper
• Submarine landslides caused by the 2024 Noto Peninsula earthquake

  2025cited by this paper
• Landslides triggered by the 2024 Noto Peninsula earthquake

  2024cited by this paper
• Refined and dynamic susceptibility assessment of landslides using InSAR and machine learning models

  2024cited by this paper
• The 2024 Noto Peninsula Earthquake: Preliminary Observations and Lessons to be Learned

  2024cited by this paper
• Modeling the 2024 Noto Peninsula earthquake tsunami: implications for tsunami sources in the eastern margin of the Japan Sea

  2024cited by this paper
• Enhancing co-seismic landslide susceptibility, building exposure, and risk analysis through machine learning

  2024cited by this paper
• Co-seismic landslide susceptibility mapping for the Luding earthquake area based on heterogeneous ensemble machine learning models

  2024influential reference
• Machine Learning Prediction of Co-Seismic Landslide with Distance and Azimuth Instead of Peak Ground Acceleration

  2024cited by this paper
• Quantitative evaluation of uncertainty and interpretability in machine learning-based landslide susceptibility mapping through feature selection and explainable AI

  2024influential reference
• Comparison of tree-based ensemble learning algorithms for landslide susceptibility mapping in Murgul (Artvin), Turkey

  2024cited by this paper
• Full seismic waveform analysis combined with transformer neural networks improves coseismic landslide prediction

  2024cited by this paper
• Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model.

  2023cited by this paper
• Analysis of the Controlling Effect of Excess Topography on the Distribution of Coseismic Landslides during the Iburi Earthquake, Japan, on 6 September 2018

  2023cited by this paper
• Coastal tsunami prediction in Tohoku region, Japan, based on S-net observations using artificial neural network

  2023cited by this paper
• Predisposing Factors for Shallow Landslides in Alpine and Hilly/Apennines Environments: A Case Study from Piemonte, Italy

  2023cited by this paper
• Does machine learning adequately predict earthquake induced landslides?

  2023cited by this paper
• An explainable AI (XAI) model for landslide susceptibility modeling

  2023cited by this paper
• Explainable artificial intelligence in geoscience: A glimpse into the future of landslide susceptibility modeling

  2023cited by this paper
• Spatial Pattern and Intensity Mapping of Coseismic Landslides Triggered by the 2022 Luding Earthquake in China

  2023cited by this paper
• Earthquake-Induced Landslide Susceptibility Assessment Using a Novel Model Based on Gradient Boosting Machine Learning and Class Balancing Methods

  2022influential reference
• Application of Tree-Based Ensemble Models to Landslide Susceptibility Mapping: A Comparative Study

  2022influential reference
• GIS-based coseismic landslide susceptibility assessment using ensemble learning approach: a case of the 2017.8.8 Jiuzhaigou earthquake event

  2021influential reference
• Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area

  2021cited by this paper
• Landslide Susceptibility Mapping Based on Random Forest and Boosted Regression Tree Models, and a Comparison of Their Performance

  2019cited by this paper
• Coseismic landslides triggered by the 2018 Hokkaido, Japan (Mw 6.6), earthquake: spatial distribution, controlling factors, and possible failure mechanism

  2019influential reference
• Factors controlling landslide frequency–area distributions

  2018cited by this paper
• The size, distribution, and mobility of landslides caused by the 2015 Mw7.8 Gorkha earthquake, Nepal

  2018influential reference
• Coseismic landslides triggered by the 8th August 2017 Ms 7.0 Jiuzhaigou earthquake (Sichuan, China): factors controlling their spatial distribution and implications for the seismogenic blind fault identification

  2018cited by this paper
• A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility

  2017cited by this paper
• A Unified Approach to Interpreting Model Predictions

  2017cited by this paper
• Automatic landslide length and width estimation based on the geometricprocessing of the bounding box and the geomorphometric analysis of DEMs

  2016cited by this paper
• Comparison of a logistic regression and Naïve Bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size

  2016cited by this paper
• Collinearity: a review of methods to deal with it and a simulation study evaluating their performance

  2013influential reference
• Scikit-learn: Machine Learning in Python

  2011influential reference
• Distribution pattern of earthquake-induced landslides triggered by the 12 May 2008 Wenchuan earthquake

  2010influential reference
• Plate subduction, and generation of earthquakes and magmas in Japan as inferred from seismic observations: An overview

  2009cited by this paper
• A Caution Regarding Rules of Thumb for Variance Inflation Factors

  2007cited by this paper
• Landslide inventories and their statistical properties

  2004cited by this paper
• Random Forests

  2001cited by this paper
• Greedy function approximation: A gradient boosting machine.

  2001cited by this paper
• Bayesian Classification (AutoClass): Theory and Results

  1996cited by this paper
• Support-Vector Networks

  1995cited by this paper
• Applied Logistic Regression, Second Edition

  1989cited by this paper
• ERROR ON CHOROPLETHIC MAPS: DEFINITION, MEASUREMENT, REDUCTION

  1971cited by this paper
• Nearest neighbor pattern classification

  1967cited by this paper
• Geology of southern Noto Peninsula central Japan, with reference to the cenozoic history

  1961cited by this paper

• No citing papers are available for this paper.