Trend analysis of machine learning application in the study of soil and sediment contamination

In recent decades, the application of machine learning methods as a powerful tool supporting accurate and representative models has become common in various fields, including pollution assessment in soil and sediment. Widespread contamination in these areas, causing severe impacts on ecosystems and...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of environmental science and technology (Tehran) Vol. 21; no. 12; pp. 8327 - 8336
Main Authors Sabour, M. R., Sakhaie, P., Sharifian, F.
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2024
Subjects
Aquatic Pollution
Earth and Environmental Science
Ecotoxicology
Environment
Environmental Chemistry
Environmental Science and Engineering
Review
Soil Science & Conservation
Waste Water Technology
Water Management
Water Pollution Control
Polycyclic aromatic hydrocarbons
Bibliometric
Heavy metals
Machine learning
Soil contamination
Online AccessGet full text

Cover

More Information
Summary:In recent decades, the application of machine learning methods as a powerful tool supporting accurate and representative models has become common in various fields, including pollution assessment in soil and sediment. Widespread contamination in these areas, causing severe impacts on ecosystems and living beings, has resulted in the development of numerous models based on machine learning techniques. These models have been used to detect, trace, and predict the extent of contamination levels and create specified management plans. This paper provides a bibliometric analysis of the evaluation of soil and sediment contamination and treatment strategies using machine learning studies from 1986 to 2022. Meaningful analysis has been done on research trends, publishing activity of journals, most active countries, subject areas, top authors, and author keywords. The research showed that China with the highest number of publications has made extensive investments and has put a special focus on this area. The most studied contaminants are heavy metals, followed by polycyclic aromatic hydrocarbons, and persistent organic pollutants. The artificial neural network followed by cluster analysis and principal component analysis are the most widely used methods.
ISSN:1735-1472
1735-2630
DOI:10.1007/s13762-024-05575-y