Prediction of lateral spreading displacement using conditional Generative Adversarial Network (cGAN)

• Published in: Soil dynamics and earthquake engineering (1984) Vol. 156; p. 107214
• Main Authors: Woldesellasse, Haile, Tesfamariam, Solomon
• Format: Journal Article
• Language: English
• Published: Barking Elsevier Ltd 01.05.2022; Elsevier BV
• Subjects: Earthquake damage; Earthquakes; Empirical analysis; Generative adversarial network (GAN); Generative adversarial networks; Ground motion; Lateral displacement; Lateral spreading displacement; Liquefaction; Machine learning; Model accuracy; Parameter identification; Parameter sensitivity; Seismic activity; Seismic response; Sensitivity analysis; Shapely values; Soil properties; Shapely values; Lateral spreading displacement; Generative adversarial network (GAN); Machine learning
• ISSN: 0267-7261; 1879-341X
• DOI: 10.1016/j.soildyn.2022.107214

Lateral spreading is the most pervasive type of earthquake-induced ground deformation, which can cause considerable damage to engineered structures and lifelines. There are several factors, such as soil properties and ground motion characteristics that affect the liquefaction induced lateral spread. This inherent complexity and nonlinear relationship between the variables make it difficult to predict lateral spread with high accuracy. There are several empirical and machine learning models developed to predict lateral spread. In this study, a conditional generative adversarial network (cGAN) is developed to predict the horizontal ground displacements. A ten-fold cross validation is used to assess the model performance. The average accuracy of the model for both free face and ground slope conditions are found to be 82% and 68%, respectively. Shapley additive explanations-based sensitivity analysis was carried out to identify the important parameters that influence the lateral displacement. •A conditional generative adversarial network (cGAN) model is used for prediction of liquefaction induced lateral spreading.•The cGAN model is presented to estimate lateral displacements for free face and gently sloping ground conditions.•The performance of cGAN model is assessed by using different size of training dataset.•A Shapley additive explanation (SHAP) method is used to interpret the predictions of cGAN model through Shapely values.