Oct 4, 2019
Brauer Hall, room 12
Dr. Ming Xu, Associate Professor
Department of Civil and Environmental Engineering
University of Michigan
Computational Approaches to Address Data Gaps in Life Cycle Assessment
Life cycle assessment (LCA) evaluates environmental impacts of a product system from its entire life cycle, from raw material acquisition to end-of-life. One of the challenges facing LCA research and practice is missing data. Due to lack of primary data or high cost of collecting primary data, LCA studies often need to make unrealistic assumptions, leading to inaccurate results. To address this challenge, we have developed new computational methods using data science tools to estimate missing data in LCA solely relying on limited known data. The first example is to estimate missing unit process data using a similarity-based approach. The intuition is that similar processes in a unit process network tend to have similar material/energy inputs and waste/emission outputs. We use the ecoinvent 3.1 unit process datasets to test our method. The results show that missing data can be accurately estimated when less than 5% data are missing in one process. The estimation performance decreases as the percentage of missing data increases. The second example is to use artificial neural network models to estimate ecotoxicity characterization factors for chemicals. These studies provide a new direction to obtain data for LCA and demonstrates a promising potential of using data science approaches for LCA data compilation.
Organizer / Host: Dr. Jun