The ability to perform pixel-wise segmentation on pavement cracks in real-time is paramount in road service condition assessment and maintenance decision-making practices. Recent deep learning detection models are focused on detection accuracy and require a large number of computing sources and long run times. However, highly efficient and accelerated models with acceptable accuracy in real-time pavement crack detection tasks are required but hard to achieve. In this work, we present a customized deep learning model architecture named Efficient Crack Segmentation Neural Network (ECSNet) for accelerated real-time pavement crack detection and segmentation without compromising performance. We introduce some novel parts, including small kernel convolutional layers and parallel max pooling and convolutional operation, into the architecture for crack information quickly extraction and model’s parameter reduction. We test latency and accuracy trade-offs of our proposed model using the DeepCrack Dataset. The results demonstrate strong performance in both accuracy and efficiency compared to other state-of-the-art models including DeepLabV3, FCN, LRASPP, Enet, Unet and DeepCrack. It is promising that ECSNet obtains the second place with an F $_{\mathbf{1}}$ score of (84.45%) and an Intersection over Union (IoU) of 73.08%. Furthermore, our model gains the largest Frames Per Second (FPS) and lowest training time among all the models which is 73.29 and 5011 seconds, respectively. It maintains a good balance between accuracy and efficiency metrics.

The detection of various cracks on pavement surfaces has drawn more and more attention from pavement maintenance engineers. In the traditional pavement image segmentation, due to the small area of the pavement cracks, the gray level of crack pixels only accounts for a very small portion in the grayscale histogram, making it difficult to segment. This paper developed an improved Otsu method integrated with edge detection and a decision tree classifier for cracking identification in asphalt pavements. An image preprocessing approach including Gaussian function‐based spatial filtering and top‐hat transform is firstly proposed to reduce the influence of poor shading and lighting effects significantly. Four edge detection operators including Prewitt, Sobel, Gauss–Laplace (LoG), and Canny are evaluated. The Canny edge detection has demonstrated outstanding performance in crack detection; this algorithm helps to obtain more details of both cracks and noises. The Sobel and LoG operators show similar image segmentation and retain fewer noises. The decision tree classifier based on the ID3 algorithm can effectively classify different types of cracks including transverse, longitudinal, and block ones.

The regional multi-hazards risk assessment poses difficulties due to data access challenges, and the potential interactions between multi-hazards and social vulnerability. For better natural hazards risk perception and preparedness, it is important to study the nature-hazards risk distribution in different areas, specifically a major priority in the areas of high hazards level and social vulnerability. We propose a multi-hazards risk assessment method which considers social vulnerability into the analyzing and utilize machine learning-enabled models to solve this issue. The proposed methodology integrates three aspects as follows: (1) characterization and mapping of multi-hazards (Flooding, Wildfires, and Seismic) using five machine learning methods including Naïve Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and K-Means (KM); (2) evaluation of social vulnerability with a composite index tailored for the case-study area and using machine learning models for classification; (3) risk-based quantification of spatial interaction mechanisms between multi-hazards and social vulnerability. The results indicate that RF model performs best in both hazard-related and social vulnerability datasets. The most cities at multi-hazards risk account for 34.12% of total studied cities (covering 20.80% land). Additionally, high multi-hazards level and socially vulnerable cities account for 15.88% (covering 4.92% land). This study generates a multi-hazards risk map which show a wide variety of spatial patterns and a corresponding understanding of where regional high hazards potential and vulnerable areas are. It emphasizes an urgent need to implement information-based prioritization when natural hazards coming, and effective policy measures for reducing natural-hazards risks in future.

Cement hydration kinetics, characterized by heat generation in early-age concrete, poses a modeling challenge. This work proposes a physics-informed neural network (PINN) named PINN-CHK designed for cement hydration kinetics, to predict early-age temperature rises in cement paste. PINN-CHK leverages data-driven solutions to craft a high-fidelity prediction model, encompassing material properties and maturity functions in cement hydration. Trained on heated cement paste data, it simultaneously fits experimental results and underlying physics, yielding a mesh-free simulation. Incorporating governing partial differential equations (PDEs), and initial and boundary conditions into its loss function, PINN-CHK architecture undergoes rigorous benchmark testing, demonstrating unparalleled predictive accuracy compared to conventional deep-learning methods. It excels in predicting complete temperature fields during spatial–temporal cement hydration, achieving a remarkable relative L2 error as low as 0.00341. PINN-CHK achieves exceptional convergence and accuracy with only 5% of the training data, ushering in a new era in this crucial field. This innovative approach bridges the gap between theory and practice, offering an attractive alternative to conventional finite element solvers for enhanced comprehension of cement hydration kinetics and concrete maturity and strength development in cement-based materials.

Pavement crack segmentation using deep learning methods can improve crack segmentation accuracy, but in many cases the training dataset is lacking or uneven, making it insufficient to train an accurate segmentation model. In this work, an integrated APC-GAN and AttuNet framework is proposed as an automated pavement surface crack pixel-level segmentation solution for small training datasets. First, an Automated Pavement Crack Generative Adversarial Network (APC-GAN) is designed for the pavement cracks data as an image augmentation method, which is modified and improved from a traditional Deep Convolutional Generative Adversarial Network (DCGAN). Then, a novel pixel-level semantic segmentation structure, Attention modified U-Net (AttuNet), is proposed by introducing the attention module into the convolutional network structure. In order to assess the performance of our proposed framework, an open-source dataset DeepCrack is used, which only contains 300 training images. The results show that our proposed APC-GAN could augment the datasets by producing more clear and distinct pavement images than DCGAN and the generated images could feature more diversity than traditional image augmentation methods. APC-GAN demonstrated higher accuracy than DCGAN and traditional image augmentation methods. Apparently, our proposed APC-GAN and AttuNet framework gains the highest value in the evaluation metrices, including recall, F1 score, mean Intersection over Union (mIoU) and mean Pixel Accuracy (mPA) among all models including U-Net, DeepLabv3, FCN, and LRASPP.

The accurate prediction of pavement performance is essential for transportation administration or management to appropriately allocate resources road maintenance and upkeep. The international roughness index (IRI) is one of the most commonly used pavement performance indicators to reflect the surface roughness. However, the existing research on IRI prediction mainly focuses on using linear regression or traditional machine learning, which cannot take into account the historical effects of IRI caused by climate, traffic, pavement construction and intermittent maintenance. In this work, a long short-term memory (LSTM)-based model, LSTM+MA, is proposed to predict the IRI of pavements using the time-series data extracted from the long-term pavement performance (LTPP) dataset. Effective preprocessing methods and hyperparameter fine-tuning are selected to improve the accuracy of the model. The performance of the LSTM+MA is compared with other state-of-the-art models, including logistic regressor (LR), support vector regressor (SVR), random forest (RF), K-nearest-neighbor regressor (KNR), fully connected neural network (FNN), XGBoost (XGB), recurrent neural network (RNN) and LSTM. The results show that selected preprocessing methods can help the model learn quickly from the data and reach high accuracy in small epochs. Also, it shows that the proposed LSTM+MA model significantly outperforms other models, with an R² of 0.965 and a mean square error (MSE) of 0.030 in the test datasets. Moreover, an overfitting score is proposed in this work to represent the severity degree of the overfitting problem, and it shows that the proposed model does not suffer severely from overfitting.