Prediction of Structural Type for City-Scale Seismic Damage Simulation Based on Machine Learning

Abstract

Being the necessary data of the city-scale seismic damage simulations, structural types of buildings of a city need to be collected. To this end, a prediction method of structural types of buildings based on machine learning (ML) is proposed herein. Specifically, using the training data of 230,683 buildings in Tangshan city, China, a supervised ML solution based on a decision forest model was designed for the prediction. The scale sensitivity and regional applicability of the designed solution are discussed, respectively, and the results show that the supervised ML solution can maintain high accuracy for different scales; however, it is only suitable for cities similar to the sample city. For wide applicability for various cities, a semi-supervised ML solution was designed based on sampling investigation and self-training procedures. The downtowns of Daxing and Tongzhou districts in Beijing were selected as a case study for the designed semi-supervised ML solution. The overall prediction accuracies of structural types for Daxing and Tongzhou downtowns can reach 94.8% and 99.5%, respectively, which are acceptable for seismic damage simulations. Based on the predicted results, the distributions of seismic damage in Daxing and Tongzhou downtown were output. This study provides a smart and efficient method for obtaining structural types for a city-scale seismic damage simulation.

Seismic damage prediction of RC buildings using machine learning

“…Sun et al 32 adopted kernel-based machine learning approaches to reconstruct seismic response demands across several tall buildings (20-42 stories). Xu et al 33 proposed a machine learning-based method to predict the structural types of buildings for city scale seismic damage simulations. Mangalathu et al 34 studied the feasibility of different machine learning techniques to classify the buildings damages to red, yellow, and green utilizing the damage data from 2014 South Nepal earthquake.…”

“…adopted kernel‐based machine learning approaches to reconstruct seismic response demands across several tall buildings (20–42 stories). Xu et al 33 . proposed a machine learning‐based method to predict the structural types of buildings for city scale seismic damage simulations.…”

Volume Expansion Rate Index Reveals the Damage Process of Surrounding Rock: A Machine Learning-Based Effectiveness Evaluation

“…For instance, Xu et al [43] proposed a real-time earthquake damage rapid reporting method, integrating ML techniques with multivariate ground motion intensity indicators to reveal a mapping relationship between strength indicators and destructive forces. Xu [44] suggested a structural type prediction method founded on ML, indicating that the multi-class decision forest algorithm optimally impacts the multi-classification of structural types and requires only minimal sampling surveys to obtain the structural type of an entire city. In addition, there are also many beneficial applications in parameter prediction in the field of Earth science study [45][46][47].…”

City Information Modeling: State of the Art

“…For computing, cloud computing can process large amounts of data within a short time, enhancing the data collection for CIM [24][25][26]. Xu et al [27] established a machine learning model to predict the structural types of buildings based on cloud computing. This model can collect data on the structural type for building groups in a large city and further enrich the CIM model.…”