Comparison between Machine Learning and Physical Models Applied to the Evaluation of Co-Seismic Landslide Hazard

A comparative methodology between advanced statistical tools and physical-based methods is carried out to ensure their reliability and objectivity for the evaluation of co-seismic landslide hazard maps. To do this, an inventory of landslides induced by the 2011 Lorca earthquake is used to highlight the usefulness of these methods to improve earthquake-induced landslide hazard analyses. Various statistical models, such as logistic regression, random forest, artificial neural network, and support vector machine, have been employed for co-seismic landslide susceptibility mapping. The results demonstrate that machine learning techniques using principal components (especially, artificial neural network and support vector machine) yield better results compared to other models. In particular, random forest shows poor results. Artificial neural network and support vector machine approaches are compared to the results of physical-based methods in the same area, suggesting that machine learning methods can provide better results for developing co-seismic landslide susceptibility maps. The application of different advanced statistical models shows the need for validation with an actual inventory of co-seismic landslides to ensure reliability and objectivity. In addition, statistical methods require a great amount of data. The results establish effective land planning and hazard management strategies in seismic areas to minimize the damage of future co-seismic landslides.

[1]  A. Paulauskaitė-Tarasevičienė,et al.  Machine Learning Algorithms for Raw and Unbalanced Intrusion Detection Data in a Multi-Class Classification Problem , 2023, Applied Sciences.

[2]  Xin Zhang,et al.  Evaluating Landslide Susceptibility Using Sampling Methodology and Multiple Machine Learning Models , 2023, ISPRS Int. J. Geo Inf..

[3]  G. Walton,et al.  An Ensemble Approach of Feature Selection and Machine Learning Models for Regional Landslide Susceptibility Mapping in the Arid Mountainous Terrain of Southern Peru , 2023, Remote. Sens..

[4]  Faming Huang,et al.  A bibliometric analysis of the landslide susceptibility research (1999–2021) , 2022, Geocarto International.

[5]  Malti Bansal,et al.  A comparative analysis of K-Nearest Neighbour, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning , 2022, Decision Analytics Journal.

[6]  N. Shahzad,et al.  A Comparative Assessment of Machine Learning Models for Landslide Susceptibility Mapping in the Rugged Terrain of Northern Pakistan , 2022, Applied Sciences.

[7]  P. Burrato,et al.  Earthquake-induced landslides susceptibility evaluation: A case study from the Abruzzo region (Central Italy) , 2022, CATENA.

[8]  Ming Wang,et al.  Rapidly assessing earthquake-induced landslide susceptibility on a global scale using random forest , 2021 .

[9]  Chih‐Heng Lu,et al.  Development of a statistics-based nowcasting model for earthquake-triggered landslides in Taiwan , 2021 .

[10]  K. Abdelrahman,et al.  Landslide hazard assessment of the Neom promising city, northwestern Saudi Arabia: An integrated approach , 2020 .

[11]  S. Martino,et al.  Obtaining suitable logic-tree weights for probabilistic earthquake-induced landslide hazard analyses , 2020, Engineering Geology.

[12]  Doug Young Suh,et al.  A Review of Machine Learning Algorithms for Cloud Computing Security , 2020, Electronics.

[13]  Chenglong Yu,et al.  Landslide Susceptibility Mapping Using the Slope Unit for Southeastern Helong City, Jilin Province, China: A Comparison of ANN and SVM , 2020, Symmetry.

[14]  Hossein Moayedi,et al.  A spatially explicit deep learning neural network model for the prediction of landslide susceptibility , 2020 .

[15]  Nadhir Al-Ansari,et al.  Shallow Landslide Susceptibility Mapping: A Comparison between Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine Algorithms , 2020, International journal of environmental research and public health.

[16]  Kounghoon Nam,et al.  An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan , 2020 .

[17]  D. Cardone,et al.  Estimating direct and indirect losses due to earthquake damage in residential RC buildings , 2019, Soil Dynamics and Earthquake Engineering.

[18]  P. Frattini,et al.  Seismic and geological controls on earthquake-induced landslide size , 2019, Earth and Planetary Science Letters.

[19]  A. Zhu,et al.  GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method , 2018 .

[20]  Wenhui Wang,et al.  Modeling Anthropogenic Fire Occurrence in the Boreal Forest of China Using Logistic Regression and Random Forests , 2016 .

[21]  Jing-Shiang Hwang,et al.  A stepwise regression algorithm for high-dimensional variable selection , 2015 .

[22]  Ligang Fang,et al.  Support vector machine modeling of earthquake-induced landslides susceptibility in central part of Sichuan province, China , 2015, Geoenvironmental Disasters.

[23]  J. J. Martínez-Díaz,et al.  Slope instabilities triggered by the 11th May 2011 Lorca earthquake (Murcia, Spain): comparison to previous hazard assessments and proposition of a new hazard map and probability of failure equation , 2014, Bulletin of Earthquake Engineering.

[24]  Chong Xu,et al.  Landslides triggered by the 12 January 2010 Port-au-Prince, Haiti, M w = 7.0 earthquake: visual interpretation, inventory compiling, and spatial distribution statistical analysis , 2014 .

[25]  B. Taner San,et al.  An evaluation of SVM using polygon-based random sampling in landslide susceptibility mapping: The Candir catchment area (western Antalya, Turkey) , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

[27]  J. G. Mayordomo,et al.  Inestabilidades de ladera provocadas por el terremoto de Lorca de 2011 (Mw 5,1): comparación y revisión de estudios de peligrosidad de movimientos de ladera por efecto sísmicoen Murcia , 2012 .

[28]  S. Martino,et al.  Widespread landslides induced by the Mw 5.1 earthquake of 11 May 2011 in Lorca, SE Spain , 2012 .

[29]  Chong Xu,et al.  GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China , 2012 .

[30]  J. Morales,et al.  Rupture directivity of the 2011, Mw 5.2 Lorca earthquake (Spain) , 2012 .

[31]  M. Marjanović,et al.  Landslide susceptibility assessment using SVM machine learning algorithm , 2011 .

[32]  J. Azañón,et al.  Constraining pre-instrumental earthquake parameters from slope stability back-analysis: Palaeoseismic reconstruction of the Güevéjar landslide during the 1st November 1755 Lisbon and 25th December 1884 Arenas del Rey earthquakes , 2011 .

[33]  J. Azañón,et al.  Regional Hazard Assessment of Earthquake-Triggered Slope Instabilities Considering Site Effects and Seismic Scenarios in Lorca Basin (Spain) , 2011 .

[34]  Witold R. Rudnicki,et al.  Boruta - A System for Feature Selection , 2010, Fundam. Informaticae.

[35]  I. Yilmaz.  Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey: conditional probability, logistic regression, artificial neural networks, and support vector machine , 2010 .

[36]  Gokhan Saygili,et al.  Probabilistic assessment of earthquake-induced sliding displacements of natural slopes , 2009 .

[37]  M. García-Rodríguez,et al.  Susceptibility assessment of earthquake-triggered landslides in El Salvador using logistic regression , 2008 .

[38]  B. Turlach.  DISCUSSION OF "LEAST ANGLE REGRESSION" BY EFRON ET AL. , 2004, math/0406472.

[39]  Roberto Giannecchini,et al.  The influence of the geological and geomorphological settings on shallow landslides. An example in a temperate climate environment: the June 19, 1996 event in northwestern Tuscany (Italy) , 2004 .

[40]  Holger R. Maier,et al.  PREDICTING SETTLEMENT OF SHALLOW FOUNDATIONS USING NEURAL NETWORKS , 2002 .

[41]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[42]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[43]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[44]  R. Jibson.  Use of landslides for paleoseismic analysis , 1996 .

[45]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[46]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[47]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[48]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[49]  N. Newmark.  Effects of Earthquakes on Dams and Embankments , 1965 .

[50]  D. Cox.  The Regression Analysis of Binary Sequences , 1958 .

[51]  J. Grzybowski,et al.  Artificial neural network ensembles applied to the mapping of landslide susceptibility , 2020 .

[52]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.

[53]  J. J. Martínez-Díaz,et al.  The Alhama de Murcia fault (SE Spain), a seismogenic fault in a diffuse plate boundary: Seismotectonic implications for the Ibero‐Magrebian region , 2004 .

[54]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.