Prediction of greenhouse gas emissions reductions via machine learning algorithms: Toward an artificial intelligence-based life cycle assessment for automotive lightweighting

Within the automotive industry, there are efforts to replace glass fiber composites to a greener yet lightweighted natural fibres as they could be reducing the environmental impacts. To know if these replacements are environmentally friendlier and how much they reduce the emissions within the life cycle of the vehicle, the gold standard is a life cycle assessment (LCA) based greenhouse gas emissions. LCA is a valuable tool, However, this method is time consuming, we have to address too many details, and it could get really complicated to perform. Artificial intelligence seems to be a very promising discipline that can easily predict a complicated inquiry. In this article, we have used machine learning to compare and predict the greenhouse emissions of replacing these materials in automotive parts. This work is unique in that it processes very limited input data, in contrast to the usual machine learning dataset. This limited data usually deter researchers from solving these kinds of problems, however, it enables us to test several artificial intelligence algorithms and input matrices to quickly predict the greenhouse gas emissions for our LCA based greenhouse gas emission saving predictions. Even though this method is not conventional and needed further discussions and testing, it is showing a very promising and easy way to predict the accurate greenhouse gas saving of these materials quickly and prior to the design of the auto parts.