PhD Research - Runsheng Song

MESM UC Santa Barbara; BEng Environmental Engineering, Huazhong University of Science and Technology (China)

Runsheng Song's research focuses on closing the data gaps in LCA using advanced computational techniques and AI models. His works have been published in accredited journals, and have been presented at several conferences. Runsheng received his bachelor’s degree in Engineering at Huazhong University of Science and Technology, China, and MESM degree from the Bren School. In his leisure time, Runsheng is an enthusiast of soccer, photography and hiking. After graduating from the Bren School, Runsheng will join the sustainability team at Amazon, working on tools to manage their supply chain and reduce the environmental impactof the company.

Dissertation Abstract:
Life Cycle Assessment (LCA) is a tool that can be used to assess the impacts of chemicals over the entire life cycle. As a large number of new chemicals are being invented every day, in many cases the necessary data to assess chemical impacts is unknown for new chemicals. In practice, LCAs are conducted in the presence of data gaps and proxy values. In the past decade, the techniques of machine learning and Artificial Intelligence (AI) have been successfully used in Environmental Science, addressing problems like climate change and weather forecasting. Now a new opportunity to improve on data deficiencies and on the quality of LCA using machine learning has emerged.

This dissertation is an attempt to harness the power of machine learning techniques to address the data deficiencies in LCA. The first chapter aims to demonstrate the method of estimating the characterized results with Artificial Neural Networks (ANNs) using chemical structure information. The second chapter aims to estimate the ecotoxicological impacts of chemicals using machine learning models, and to calculate the Effect Factors (EFs) in LCA. The last chapter of this dissertation aims to reduce the uncertainty of an existing chemical fate model using machine learning techniques. Altogether, the outcomes of this dissertation provide new methods to estimate the necessary parameters in LCA, allowing LCA studies to be conducted at screening level with reliable accuracy.

 

Year Admitted : 2015
Research areas:  Life Cycle Assessment, Chemical Toxicity, Data Science
Faculty Advisor: Arturo Keller and Sangwon Suh


Lab Page
LinkedIn

Projects

Chemical Life Cycle Collaborative (CLiCC) Project – Network for Characterizing Chemical Life Cycle (NCCLC) funded by the EPA; Incorporating Land Use Impacts on Biodiversity into Life Cycle Assessment for the Apparel Industry