Accurate seismic ground response analysis is crucial for the design and safety of civil infrastructure and establishing effective mitigation measures against seismic risks and hazards. This is a complex process due to the nonlinear soil properties and complicated underground geometries. As a simplified approach, the one-dimensional wave propagation model, which assumes that seismic waves travel vertically through a horizontally layered medium, is widely adopted for its reasonable performance in many practical applications. This study explores the potential of sequence deep learning models, specifically 1D convolutional neural networks (1D-CNNs), long short-term memory (LSTM) networks, and transformers, as an alternative for seismic ground response modeling. Utilizing ground motion data from the Kiban Kyoshin Network (KiK-net), we train these models to predict ground surface acceleration response spectra based on bedrock motions. The performance of the data-driven models is compared with the conventional equivalent-linear analysis model, SHAKE2000. The results demonstrate that the deep learning models outperform the physics-based model across various sites, with the transformer model exhibiting the smallest average prediction error due to its ability to capture long-range dependencies. The 1D-CNN model also shows a promising performance, albeit with occasional higher errors than the other models. All the data-driven models exhibit efficient computation times of less than 0.4 s for estimation. These findings highlight the potential of sequence deep learning approaches for seismic ground response modeling.

Open-graded aggregates (OGAs) are free-draining materials often used as the base layer of permeable pavements to allow the infiltration or drainage of stormwater. Despite their widespread use, the compaction quality of OGA base layers has not been specified properly. The currently used density-based compaction quality control (QC) has limitations; obtaining the field density and maximum dry density of OGAs by typical methods is challenging, due to their unique properties. To overcome these limitations, modulus-based compaction QC can be used as an alternative. In this study, five different OGAs were chosen and compacted into a specially built soil chamber to measure their densities. The light weight deflectometer (LWD) and the soil stiffness gauge (SSG) were used to evaluate the modulus of the compacted OGAs. The vibratory hammer compaction test was conducted to obtain the maximum dry density of the aggregates. Through these tests, the relationship between the modulus of the compacted aggregates and the relative density was obtained, and efforts to find a modulus range that ensures proper compaction were made. It was found that the LWD and SSG are valid and reliable devices for monitoring the modulus change of OGAs due to compaction.

The permeable pavement is one of Low Impact Development technics that allows stormwater to infiltrate through the pavement surface and the underlying base layer, thereby reducing surface runoff and preventing water contamination. For permeable base layers of permeable pavements, open-graded aggregates are often used to infiltrate and store stormwater in the pore of aggregate base layers. The mechanical behavior of open-graded aggregates has not been a major interest of pavement industry and society, and therefore there is much less information known for behavior of compacted open-graded aggregates comparing to dense-graded materials. This study aims at investigating the mechanical behavior of compacted permeable or open-graded aggregate base materials based on field experiments. Five different open-graded aggregates were selected, and they were compacted in the field up to 12 passes with a 10-ton vibratory compaction roller. The mechanical behaviors of aggregates were evaluated by conducting plate load tests at 2, 4, 8, and 12 passes of roller. For the test conditions considered herein, the strain modulus at the first loading seems to provide more consistent results with respect to aggregate types and level of compaction than other stiffness measures from plate load tests.

The efficient and accurate detection of cracks in concrete structures is critical for maintaining structural integrity and safety. This study compares two state-of-the-art convolutional neural network (CNN) models, Mask R-CNN and YOLOv8, for automated concrete crack detection, each model representing two mainstream approaches for object detection and instance segmentation: single-stage and two-stage approach. We evaluate both models on 1,203 concrete images with 7:2:1 training, testing, and validation split, and assess their accuracy and processing speed. Mask R-CNN achieves a mean Intersection over Union (IoU) of 96.5% with a minimum IoU of 77% and higher consistency, compared to YOLOv8’s 90.6%, which often shows complete failure with IoU of 0%. In terms of computation speed, YOLOv8 shows 0.3225 s of average processing time per image, slightly outperforming the speed of Mask R-CNN, 0.4867 s. Despite YOLOv8’s faster processing speed, considering the characteristics of concrete crack detection tasks where accuracy should be prioritized over speed, Mask R-CNN seems a more proper model for reliable crack detection. We also show the accuracy of Mask R-CNN for crack detection tasks can be further enhanced by employing the ResNeXt backbone.