The adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein, we present the effectiveness of automated deep learning in enhancing the assessment of damage caused by the 2017 Pohang earthquake. Six classical pre-trained convolutional neural network (CNN) models are implemented through transfer learning (TL) on a small dataset, comprising 1780 manually labeled images of structural damage. Feature extraction and fine-tuning TL methods are trained on the image datasets. The performances of various CNN models are compared on a testing image dataset. Results confirm that the MobileNet fine-tuned model offers the best performance. Therefore, the model is further developed as a web-based application for classifying earthquake damage. The severity of damage is quantified by assigning damage assessment values, derived using the CNN model and gradient-weighted class activation mapping. The web-based application can effectively and automatically classify structural damage resulting from earthquakes, rendering it suitable for decision making, such as in resource allocation, policy development, and emergency response.

Conventionally, liquefaction-induced settlements have been predicted through numerical or analytical methods. In this study, a machine learning approach for predicting the liquefaction-induced settlement at Pohang was investigated. In particular, we examined the potential of an artificial neural network (ANN) algorithm to predict the earthquake-induced settlement at Pohang on the basis of standard penetration test (SPT) data. The performance of two ANN models for settlement prediction was studied and compared in terms of the R² correlation. Model 1 (input parameters: unit weight, corrected SPT blow count, and cyclic stress ratio (CSR)) showed higher prediction accuracy than model 2 (input parameters: depth of the soil layer, corrected SPT blow count, and the CSR), and the difference in the R² correlation between the models was about 0.12. Subsequently, an optimal ANN model was used to develop a simple predictive model equation, which was implemented using a matrix formulation. Finally, the liquefaction-induced settlement chart based on the predictive model equation was proposed, and the applicability of the chart was verified by comparing it with the interferometric synthetic aperture radar (InSAR) image.

The sand-cone method is commonly used to measure the in situ density of compacted soils. While determining field density with this method, differences in the sand-filling process between the test hole and the calibration container can cause errors. The differences can result from various in situ conditions such as the shape and size of the test hole and the moisture conditions of the filling sand and test ground. Temporary rainfall can increase the moisture content of both in situ soils and filling sand. This study examined the effect of wetting conditions on the accuracy of the sand-cone method in a laboratory. Compacted soils with different water contents (2–16%) were prepared in a small circular container in the laboratory, and the sand-filling process was simulated for cylindrical, conical, and roof-shaped test holes with depths of 10 and 15 cm. As the water content of the compacted soils increased, the sand-cone method underestimated the volume of sand accumulated in the test holes by up to 20%, resulting in the calculated density being overestimated by an identical amount. Slightly moist sand was poured into artificial test holes. When the water content of the filling sand was below 1%, no significant error was observed in the calculated volume.