Computational Approaches for Estimating Life Cycle Inventory Data

life cycle assessment;link prediction;data estimation;Natural Resources and Environment

Cai, JiaruiLiang, Sai ;

University of Michigan

关键词: life cycle assessment;    link prediction;    data estimation;    Natural Resources and Environment;   

Others  :  https://deepblue.lib.umich.edu/bitstream/handle/2027.42/134693/Cai_Jiarui_Document.pdf?sequence=3&isAllowed=y

瑞士|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Data gaps in life cycle inventory (LCI) are stumbling blocks for investigating the life cycle performance and impact of emerging technologies. It can be tedious, expensive and time consuming for LCI practitioners to collect LCI data or to wait for experimental data become available. Ipropose a computational approach to estimate missing LCI data using link prediction techniques in network science. LCI data in Ecoinvent 3.1 is used to test themethod. The proposedapproach is based on the similarities between differentprocesses or environmental interventions in the LCI database. By comparing two processes’ material inputs and emission outputs, Imeasure the similarity of these processes. Ihypothesize that similarprocesses tend to have similar material inputs and emission outputs which are life cycle inventory data Iwant to estimate. In particular, Imeasure similarity using four metrics, including average difference, Pearson correlation coefficient, Euclidean distance, and SimRank with or without data normalization.Itest these four metricsandnormalization methodfor their performance of estimating missing LCI data.Theresults show that processes in the same industrial classification have higher similarities,which validate theapproach of measuring the similarity between unit processes. Iremove a small set of data (from one data point to 50) for each process and then use the rest of LCI data as to train the model for estimating the removed data. It is foundthat approximately 80% of removed data can be successfully estimated with less than 10% errors. This study is the first attempt in the searching for an effective computational method for estimating missing LCI data. It isanticipatedthat this approach will significantly transform LCI compilation and LCA studies in future.