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. 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, a set of models of pavement LCA considering every factor of the pavement life cycle phases is needed. 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. A total of 141 Canadian road sections from the Long Term Pavement Performance (LTPP) database are considered to develop models using machine learning algorithms: multiple linear regression, polynomial regression, decision tree regression and support vector regression. These models determine the significant contributors and quantify the CO₂ emission in material production, initial construction, maintenance and use phase. The study also reveals the contribution of Canadian provinces’ CO₂ emission involved in the life of a pavement.

摘要

路面生命周期评估（LCA）是一种综合方法，可评估路面的环境影响。它采用从摇篮到坟墓的方法来评估路面寿命的关键阶段。以前的LCA案例研究使用了各种不同的功能单元和因素，以实现不同的目标和范围。这些不一致的功能单元和因素在理解初始施工过程中对环境影响的全貌时造成混乱。因此，需要一套考虑路面生命周期各阶段因素的路面LCA模型。加拿大是一个非常大的国家，不同的省份拥有不同的人行道建设实践。因此，这项工作的目的是开发一套用于量化CO ₂的有用模型加拿大路面施工的排放量。长期路面性能（LTPP）数据库中的总共141条加拿大路段被认为使用机器学习算法开发模型：多元线性回归，多项式回归，决策树回归和支持向量回归。这些模型确定了重要的贡献者，并量化了材料生产，初始构造，维护和使用阶段的CO ₂排放量。该研究还揭示了加拿大各省的CO ₂排放量对路面寿命的影响。