École Spéciale des Travaux Publics

Smart city initiatives highlight the vital role of Intelligent Transportation Systems (ITS), which remain underexplored with limited AI-driven solutions integration in real-time urban traffic management across African cities. ITS is crucial to enhance urban mobility efficiency and sustainability to address growing mobility challenges in the era of swift African urbanization. This paper proposes an AI-driven predictive model for the Travel Time Index (TTI), a key metric quantifying urban traffic congestion and mobility performance. Using spatio-temporal analysis, neural networks, and advanced machine learning algorithms, the model processes real-time, multimodal traffic data, capturing congestion patterns, TTI fluctuations, and complex urban travel dynamics, focusing on Casablanca, Morocco, as a smart city case study. Five predictive modeling approaches were carefully selected and rigorously evaluated: Multivariate Linear Regression (MLR), Random Forest (RF), Gradient Boosting, Multilayer Perceptron (MLP), and Support Vector Regression (SVR). Their performance was assessed using standard evaluation metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2). All models achieved high accuracy, with Random Forest ranking highest (MAE = 0.315, R2 = 0.985). Beyond prediction, the methodology incorporates feature importance analysis and hyperparameter tuning via GridSearchCV to improve operational performance and practical applicability across evolving traffic ecosystems. Hyperparameter optimization further enhanced Random Forest’s accuracy (MAE = 0.220, R2 = 0.988). The findings demonstrate improved travel time estimation and congestion management capabilities, offering a scalable, adaptable framework to guide data-driven mobility strategies in diverse urban settings and provide actionable insights for urban planners, policymakers, and mobility stakeholders.

International audience

The construction industry’s escalating energy demands and greenhouse gas emissions underscore the need for sustainable, high-performance building materials. This study investigates the incorporation of locally sourced alfa fibers (AFs) into plaster-based composites to enhance thermal insulation, reduce environmental impact, and lower production costs. Three distinct AF morphologies—small (<5 mm), medium (10 ± 5 mm), and large (20 ± 5 mm)—were incorporated at fixed mass ratios, and their effects on key material properties were systematically evaluated. The results indicate that integrating AFs into plaster reduces composite density by up to 16.5%, improves thermal characteristics—lowering thermal conductivity and diffusivity by up to 52%—and diminishes both CO2 emissions and production costs. The addition of fibers also enhances flexural strength (up to 40%) through a fiber bridging mechanism that mitigates crack propagation, although a general decline in compressive strength was observed. Notably, composites containing medium and large fibers achieved significantly lower densities (~1050 kg/m3) and superior thermal insulation (~0.25 W/mK) compared with those with small fibers, with the largest fibers delivering the greatest thermal performance at the expense of compressive strength. Overall, these findings highlight the potential of AF–plaster composites as environmentally responsible, high-performance building materials, while emphasizing the need to carefully balance mechanical trade-offs for structural applications.

This study uses a systematic literature review using the PRISMA methodology to investigate how digital technologies help the construction industry implement the principles of the circular economy. Building information modeling (BIM), the Internet of Things (IoT), blockchain, and artificial intelligence (AI) are identified in the study as key technologies supporting circular strategies that aim to reduce resource use, promote reuse, facilitate disassembly, and enable high-value recycling. The study is based on ninety-one pertinent publications. The operational phase, which is essential for long-term sustainability, is understudied, according to the findings, which show that the majority of research concentrates on the design, construction, and end-of-life phases. Furthermore, there are a number of obstacles to the integration of these technologies, such as the lack of standardized data formats, the requirement for professionals to possess particular digital skills, and the absence of unified regulations. Overall, digital tools hold significant potential to accelerate the transition of the building industry toward circularity. To overcome present constraints, more applied research is necessary. To break down current silos and guarantee the successful adoption of circular practices aided by digital technologies, scalable solutions and improved interdisciplinary collaboration are required.

International audience