Published in Scientific Papers. Series E. Land Reclamation, Earth Observation & Surveying, Environmental Engineering, Vol. XIV
Written by Sneha BASKARAN, Ezhilmaran DEVARASAN
This article investigates the evolving landscape of machine learning and its application in waste management from 2014 to 2024, utilizing data from Scopus and employing the VOSviewer software for bibliometric analysis. The research identified 217 articles related to machine learning in waste management. Our analysis aimed to assess metrics such as yearly publication trends, citation rates, top publishing countries, and the most influential authors in the field. Additionally, we examined the evolution of research on machine learning in waste management, focusing on highly cited articles, leading journals, authors' keywords, co-citation patterns, and co-authorship networks among countries and organizations. This comprehensive review provides a deeper understanding of the growth and collaborative nature of the field. The results indicate a notable rise in machine learning publications in waste management, increasing from 1 in 2016 to 62 in 2024, for a total of 217 publications. China, India, and South Korea led the research output, contributing 19.35%, 15.67%, and 10.60%, respectively. Leading journals such as the Journal of Cleaner Production, Waste Management, and Sustainability Switzerland emerged as critical contributors. A sharp increase in publications was observed post-2020, especially in the Journal of Cleaner Production. One of the most notable findings was the high citation rate of research on machine learning techniques in waste management, underscoring their practical relevance and mathematical significance in optimizing waste handling and reduction. Frequently occurring keywords included "machine learning", "waste management", and "deep learning". The VOSviewer visualizations indicated strong international collaboration networks, highlighting a robust global research framework. Our study emphasizes the growing influence of machine learning in waste management, marked by increasing research activity and international cooperation, and showcases the transformative potential of machine learning driven models in improving global waste management practices.
[Read full article] [Citation]
