Abstract:
Pavement Life Cycle Assessment (LCA) is a comprehensive method to evaluate the environmental impacts of a pavement section. It employs a cradle-to-grave approach assessing critical stages of the pavement’s life. Pavement LCA tools require a great amount of data to estimate the environmental impact. In the literature, previous LCA case studies used a wide variety of different functional units and factors in order to achieve different goals and scopes. These inconsistent functional units and factors create confusion in understanding the complete picture of environmental impact during the initial construction. Therefore, there a need for a set of models of pavement LCA considering every factor of the pavement life cycle phases. Canada is a very large country and the different provinces have different pavement construction practices. Therefore, the goal of this work is to develop a set of useful models for quantifying CO2 emission from pavement construction in Canada. To realize this goal, a total of 141 Canadian road sections from the Long Term Pavement Performance (LTPP) database are considered to develop a set of models using machine learning algorithms. Multiple linear regression, polynomial regression, decision tree regression and support vector regression concepts are used to build these models. These models determine the significant contributors and quantify the CO2 emission in pavement material production, initial construction, maintenance and use phase. Using the model validation technique, the usefulness of these models is also assessed. The study also reveals the contribution of Canadian provinces’ CO2 emission from various phases involved in the life of a pavement. The proposed LCA models will help in the decision-making process of adjusting variables in pavement life cycle-based environmental analysis.
Contributors: Alam R, Hossain K.
Link(s) for the Paper: Journal Website |ResearchGate