A graph database for life cycle inventory using Neo4j. (20th March 2023)

• Record Type: Journal Article
• Authors: Saad, Mohamed; Zhang, Yingzhong; Tian, Jinghai; Jia, Jia
• Is Part Of: Journal of cleaner production. Volume 393(2023)
• Publication Date: 2023-03-20
• Subjects: Life cycle inventory -- Labeled property graph -- Neo4j database management system -- Graph database -- Knowledge graph; Factory and trade waste -- Management -- Periodicals; Manufactures -- Environmental aspects -- Periodicals; Déchets industriels -- Gestion -- Périodiques; Usines -- Aspect de l'environnement -- Périodiques; 628.5
• DOI: 10.1016/j.jclepro.2023.136344
• Languages: English
• ISSNs: 0959-6526

Abstract

Abstract: Life cycle inventory (LCI) databases constitute the basis for the life cycle assessment (LCA) of a product system. LCI data involve complex relationships between the production activities and the environment. The currently used relational database employs a rigid schema structure of two-dimensional tables and lacks direct support for the complex relationships between LCI data. In this paper, a graph database was designed and constructed using Neo4j graph database management system. First, an LCI knowledge graph (LCIKG) model for the graph database is proposed, which employs the labeled property graph structure and describes the LCI data and the semantic relationships among LCI data concepts. Second, Ecoinvent datasets were successfully used to construct the LCI graph database by automatically extracting Cypher syntax patterns; then, Neo4j was used to store, visualize, and retrieve LCI data. Finally, a set of queries have been executed to evaluate the performance of the graph database; a case study has been provided to demonstrate the effectiveness of the proposed graph database. The graph database can effectively reduce the time and effort to query and process LCI data of a product system. Moreover, the dynamic schema of the LCIKG model promotes the scalability and interoperability of LCI data. The completed work provides a feasible solution for the issues and challenges in current LCI research and promotes the wide application of LCA. Highlights: Using graph databases to replace traditional relational databases to store and manage LCI data. A novel labeled property knowledge graph model for LCI data (LCIKG) is proposed and developed. An approach based on Cypher syntax patterns to automatically extract nodes and relations of LCIKGs from Ecoinvent datasets. The wide application prospects of the LCI graph database are shown.