Transfer Learning for Improving Seismic Building Damage Assessment

Ying Wang,Leibin Wang,Huaxiang Yin,Sanjit Kumar Mondal,Tianyu Ci,Qigen Lin

doi:10.3390/rs14010201

Abstract

The rapid assessment of building damage in earthquake-stricken areas is of paramount importance for emergency response. The development of remote sensing technology has aided in deriving reliable and precise building damage assessments of extensive areas following disasters. It is well documented that convolutional neural network methods have superior performance in earthquake building damage assessment compared with traditional machine learning methods. However, deep learning models require a large number of samples, and sufficient numbers of samples are usually not available in the newly earthquake-stricken areas rapidly enough. At the same time, the historical samples inevitably differ from the new earthquake-affected areas due to the discrepancy of regional building characteristics. For this purpose, this study proposes a data transfer algorithm for evaluating the impact of a single historical training sample on the model performance. Then, beneficial samples are selected to transfer knowledge from the historical data for facilitating the calibration of the new model. Four models are designed with two earthquake damage building datasets and the performance of the models is compared and evaluated. The results show that the data transfer algorithm proposed in this work improves the reliability of the building damage assessment model significantly by filtering samples from the historical data that are suitable for the new task. The performance of the model built based on the data transfer method on the test set of new earthquakes task is approximately 8% higher in overall accuracy compared with the model trained directly with the new earthquake samples when the training data for the new task is only 10% of the historical data and is operating under the objective of four classes of building damage. The proposed data transfer algorithm has effectively enhanced the precision of the seismic building damage assessment in a data-limited context. Thus, it could be applicable to the building damage assessment of new disasters.

Highlights

The performance of the visual geometry group network (VGG)-OR(LD) model in the new task decreases significantly when the damage classes are divided into three categories (Set 2: nearly intact, severe damage, and complete collapse), yet the overall accuracy is 74% and the kappa coefficient value is 0.6, which is comparable to the performance of the existing models in the literature [28,45,46]
10% ofThe theresults historiof this study show that when the training set of the new task reaches about of the cal data, i.e., 1000 samples, combined with the data augmentation method, the model has historical data, i.e., samples, combined with the data augmentation method, the been able to achieve an overall accuracy of about 74% for the VGG-OR(DT) model derived model has been able toinachieve an overall accuracy of about for the4: VGG-OR(DT)
This study investigates the effective use of historical data and the extrapolation performance of the existing trained models to new or unknown data through transfer learning approaches, attempting to address the limitations of deep learning models in practical seismic building damage assessment applications

Summary

Introduction

Major earthquakes are one of the most destructive and devastating natural disasters, often triggering extensive secondary disasters that result in widespread building collapse and infrastructure damage [1,2,3,4,5]. In this context, the extensive building damage triggered by earthquake disasters is an overwhelming cause of human casualties and loss of assets [6,7]. Assessing the damage of the building during the emergency response period following the earthquake is an essential process, which would help to mitigate the loss of Remote Sens. Satellite or UAV-based imagery allows for faster, more precise, and more extensive coverage of the disaster-affected area, which could be analyzed for building damage assessment purposes, which could support the emergency response [11,12]

Objectives

Methods

Results

Conclusion