Research trends in spatial modeling of PM2.5 concentration using machine learning: a bibliometric review

Abstract

Spatial modeling is commonly used to map research variables, including particulate matter 2.5 (PM2.5) concentrations, in specific areas. The article that surveys publications on the application of machine learning in spatial modeling of PM2.5 using bibliometric methods has not been identified yet. This paper aims to analyze trends in applying machine learning in the spatial modeling of PM2.5 using bibliometric methods. The review was conducted on publications indexed in the Scopus database over the decade (2014–2023) comprising 335 articles. The analysis included co-authorship and co-occurrence using VOSviewer. From the two stages of analysis, it can be concluded that research on this topic has constantly increased over the past 10 years, with the highest productivity coming from researchers in China. This research topic is multidisciplinary, with most publications appearing in environmental science. The research also shows a very high collaboration rate of 0.98. A deeper examination of the keywords reveals the most commonly used machine learning techniques by researchers. The random forest method is the most frequently found in the analyzed documents, followed by deep learning, long short-term memory (LSTM), extreme gradient boosting (XGBoost), and ensemble model.