Machine Learning and Aerodynamic Optimization for Heavy Road Transportation

The need to reduce fossil fuel use is urgent, especially in sectors that produce a lot of greenhouse gases like heavy-duty road transportation. This is necessary because of increasing energy demand, urbanization, and global climate change. In Canada alone, more than $30 billion is spent yearly on fuel for heavy vehicles, resulting in a large amount of CO2 emissions. To address this problem, researchers are working on cost-effective changes to improve vehicle aerodynamics. These modifications could potentially reduce fuel consumption by 5-10%. Implementing these changes could lead to a decrease of up to 3 megatons of CO2 emissions in Canada and over 100 megatons worldwide. Combining machine learning with aerodynamics will further enhance these efforts by improving designs and predictions. This progress paves the way for a more sustainable and environmentally friendly future in heavy-duty road transportation, making a significant impact on mitigating global climate change.

Faculty Supervisor:

Mohammad Saeedi

Student:

Partner:

Greentech Innovations

Discipline:

Engineering

Sector:

Administrative and support, waste management and remediation services

University:

Dalhousie University

Program: