Graduate Researcher in Structural Engineering | Sharif University of technology | Iran
Alireza Javid is a civil and structural engineering researcher whose work centers on sustainable construction materials, structural health monitoring, and the integration of advanced machine learning techniques into structural assessment and design. He holds an M.Sc. in Structural Engineering from Sharif University of Technology, where his research investigated the effects of high temperatures on cement bonding and pozzolanic concrete. His scholarly contributions reflect a strong interdisciplinary foundation, bridging experimental mechanics, data-driven modeling, and computational optimization. Javid has authored multiple peer-reviewed journal articles in high-impact international outlets, with published work addressing machine learning–based predictions of concrete compressive strength, bond behavior in FRP–timber systems under thermal cycling, high-temperature concrete overlay interactions, and the mechanical characterization of industrial by-product concrete. His publications collectively exceed 40 citations, demonstrating growing recognition within the structural materials and AI-in-construction communities. His research also extends to ultrasonic pulse velocity prediction, temperature-dependent performance of fiber-reinforced concrete, and microstructural deterioration of FRP composites in aggressive environments. Several manuscripts under review explore impact resistance of stabilized rammed earth, acid-rain durability of composite materials, and environmental effects on geopolymer concretes. In addition, he is preparing works on crack simulation, nano-engineered materials, and deep-learning-based crack classification, highlighting his expanding focus on intelligent infrastructure systems. As a research assistant at Sharif University of Technology, Javid has developed high-accuracy predictive models using CatBoost, gradient boosting, and novel optimization algorithms, achieving R² values up to 0.99 across various structural datasets. His work consistently emphasizes societal needs such as sustainability, material efficiency, and resilience under extreme conditions.
Publications
Javid, A., & Toufigh, V. (2024). Utilizing ensemble machine learning and gray wolf optimization to predict the compressive strength of silica fume mixtures. Structural Concrete, 25(5), 4048–4074.
Javid, A., Javid, E., & Toufigh, V. (2025). High-temperature bond strength evaluation of concrete overlays with industrial by-products: Experimental and analytical approaches using machine learning. Engineering Applications of Artificial Intelligence, 153, 110954.
Lotfalipour, F., Javid, A., & Toufigh, V. (2025). Boosting algorithms for predicting the bond properties of timber and fiber reinforced polymer (FRP) under thermal cycling using single-lap shear tests. European Journal of Wood and Wood Products, 83(2), 83.
Mohsennia, E., Javid, A., & Toufigh, V. (2025). Advanced machine learning techniques for predicting compressive strength and ultrasonic pulse velocity of concrete incorporating industrial by-products. Case Studies in Construction Materials, e04801.
Javid, A., Kamali, H., & Toufigh, V. (2025). Compressive strength prediction of fiber-reinforced concrete under varied temperature conditions using machine learning. Construction and Building Materials, 504, 144648.