# Machine Learning and Artificial Intelligence in Circular Economy: A Bibliometric Analysis and Systematic Literature Review

**Authors:** Abdulla All noman, Umma Habiba Akter, Tahmid Hasan Pranto, AKM Bahalul Haque  
**arXiv:** [2205.01042](https://arxiv.org/abs/2205.01042)  
**Date:** 2022-04-01  
**Summary page:** https://www.summarizepaper.com/en/paper/2205.01042v1/

## Key points

- Improper and unorganized use of limited raw materials leads to excessive waste production that harms the environment and ecosystem
- Traditional linear production lines fail to address waste production and shorter product life cycle issues
- Circular economy (CE) is a prospective concept that aims to complete the product life cycle loop by bringing out the highest values from raw materials in the design phase and later on by reusing, recycling, and remanufacturing
- Artificial intelligence (AI) and machine learning (ML) can assist in effectively adopting and implementing CE in real-world practices
- A bibliometric analysis was conducted on 104 SCOPUS indexed documents exploring critical research criteria in AI and CE
- The study revealed that these documents were published in 70 publication mediums such as journals and conferences, with a total of 1184 keywords comprising author keyword and index keyword detected by VOS Viewer
- The average number of authors per document was found to be 3.25, with single-authored documents totaling 17 while multi-authored documents made up the rest
- Collaboration between 32 countries was observed, with participation from 384 authors across different organizations engaged in this research.
- Bibliometric analysis using SMACOF algorithm was used to extract prevalent information from the collected documents.
- This study provides comprehensive research insights and trends in AI and CE integration, with identified research gaps needing further attention discussed.

## Summary

The improper and unorganized use of limited raw materials has led to the production of an excessive amount of waste, which is detrimental to our environment and ecosystem. Traditional linear production lines have failed to address far-reaching issues like waste production and a shorter product life cycle. However, a prospective concept known as circular economy (CE) has shown promising prospects for adoption at industrial and governmental levels. CE aims to complete the product life cycle loop by bringing out the highest values from raw materials in the design phase and later on by reusing, recycling, and remanufacturing. Innovative technologies such as artificial intelligence (AI) and machine learning (ML) provide vital assistance in effectively adopting and implementing CE in real-world practices. This study explores the adoption and integration of applied AI techniques in CE through bibliometric analysis on a collection of 104 SCOPUS indexed documents exploring critical research criteria in AI and CE. From these documents, 40 papers were selected for a systematic literature review. The primary information gathered from these 104 documents revealed that they were published in 70 publication mediums such as journals and conferences, with a total of 1184 keywords comprising author keyword and index keyword detected by VOS Viewer. The average number of authors per document was found to be 3.25, with single-authored documents totaling 17 while multi-authored documents made up the rest. A total of 39 countries' documents were found where collaboration between 32 countries was observed, with participation from 384 authors across different organizations engaged in this research. The number of citations for these 104 documents was found to be 622, with an average citation rate of 5.98 per document. The types of documents used included journal articles (53), conference papers (48), and book chapters (6). Bibliometric analysis using SMACOF algorithm was used to extract prevalent information from the collected documents. The algorithm carried out an optimization strategy from multidimensional data to observe the relationship of different parameters on a specific area or field of research. Overall, this study provides comprehensive research insights and trends in AI and CE integration, with identified research gaps needing further attention and future research directions discussed.