Engineered bamboo has recently received lots of attention of civil engineers and professional researchers due to its better mechanical performance than that of softwood timber. Parallel strand bamboo is one important part of engineered bamboo for its excellent durable performance compared to the laminated veneer bamboo. The required curing temperature in hot-pressing process is usually higher than 120°C to reduce the content of nutritional ingredients and hemy cellulose, and to avoid the decay from the environment and insects. Nonetheless, the appearance of engineered bamboo gets darker with the increase of temperature during the hot-pressing process. In order to minimize the color deepening while maintaining the durability, a high-durable parallel strand bamboo (HPSB) with relative high hot-pressing temperature (140°C) was produced and tested. The present study investigates the mechanical performance through tension, compression, shear and bending tests. The experimental behavior of the specimens was identified, including the failure mode and load-displacement relationship. It was demonstrated that the HPSB material had better mechanical performance parallel to grain, making it as a considerable structural material. The average elastic modulus parallel to grain was 14.1 GPa, and the tensile and compressive strengths were 120.7 MPa and 121.0 MPa, respectively. The tension perpendicular to grain should be avoided in the practical application due to the lower strength and elastic modulus. Two stress-strain relationships of tension and compression parallel to grain, including three-linear and quadratic function models, were proposed and compared with the experimental results. The three-linear model was then applied to the finite element model. The finite element analysis using ANSYS software was conducted to validate the feasibility of the constitutive relationship. The quadratic function model showed better agreement with the experimental results, but the three-linear relationship was also precise enough to analyze the bending tests of HPSB material, whereas being less accurate to describe the elastic-plastic compression behavior.

A substantial proportion of construction accidents is associated with unsafe worker behavior. Identifying their underlying mechanism is vital for designing effective interventions. As prior studies could not capture complex nonlinear interactions among organizational and individual factors, this study leverages machine learning (ML) techniques, which can capture complex relationships by handling large datasets, and can identify patterns in worker behavior. The study proposes an explainable ML model to interpret key determinants of safe behavior. The data were collected from 425 construction workers in Saudi Arabia. Multiple ensemble and benchmark ML algorithms—including random forest (RF), categorical boosting, decision jungle, light gradient boosting machine, support vector machine, and adaptive boosting—were implemented and compared. The results indicate that the RF model achieved the best predictive performance, outperforming several competing models. To enhance the model’s interpretability, explainable artificial intelligence (XAI) techniques were applied to reveal the interaction of key predictors influencing workers’ behaviors. The results demonstrate that safety communication, risk perception, and supportive work environment are the most influential determinants shaping safety behavior. As a key novelty, this study introduces an ML-based approach for predicting construction workers’ safety behavior and applies XAI techniques to systematically interpret the key determinants of safety behavior. The results also provide valuable insights for safety managers and offer data-driven guidance to enhance the effectiveness of safety interventions.