Optimization of Carbon Emissions in Asphalt Pavement Construction

Abstract

This paper investigates the optimization of carbon emissions in asphalt pavement construction by deep Q-learning. The study developed a model to identify optimal hybrid systems that are environmentally and cost-effective. The optimized system resulted in a 5% reduction in CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emissions compared to the classical methods, significant improvements in energy consumption, water use and hazardous waste generation in Besides, the inclusion of plastic waste in asphalt mix not only increased the sustainability but also saved costs by 0.8%. The results demonstrate the effectiveness of deep Q-learning to overcome challenging optimization challenges in pavement construction, to promote environmental and economic benefits. Despite the computational demands of the model, the findings highlighted the potential of advanced Deep learning techniques to increase product sustainability and efficiency. The integration of deep Q-learning provides a new approach to construction optimization, significantly reducing carbon emissions and operating costs while promoting sustainable development.