Related Experiment Video
Updated: Jun 15, 2025
10:20
Quantification of Heavy Metals and Other Inorganic Contaminants on the Productivity of Microalgae
Published on: July 10, 2015
15.9K
Utilizing machine learning to evaluate heavy metal pollution in the world's largest mangrove forest
Ram Proshad1, Md Abdur Rahim2, Mahfuzur Rahman3
1State Key Laboratory of Mountain Hazards and Engineering Safety, Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, Sichuan, China; University of Chinese Academy of Sciences, Beijing 100049, China.
The Science of the Total Environment
|August 25, 2024
Summary
Heavy metal pollution threatens the Sundarbans mangrove forest. Machine learning models accurately predict sediment contamination, identifying critical areas for conservation and management interventions.
Area of Science:
- Environmental Science
- Ecotoxicology
- Geochemistry
Background:
- The Sundarbans, the world's largest mangrove forest, faces severe ecological and health risks due to heavy metal pollution.
- Accurate prediction of heavy metal accumulation in Sundarbans sediments has been a significant challenge.
Purpose of the Study:
- To develop and evaluate machine learning models for predicting heavy metal sediment pollution in the Sundarbans.
- To identify the most effective algorithms for modeling the accumulation of eleven heavy metals.
Main Methods:
- Collected 199 standardized sediment samples from the Sundarbans.
- Applied ten different machine learning algorithms, including Extremely Randomized Trees, Random Forest, and Decision Trees.
- Utilized feature attribute analysis and spatial autocorrelation (Moran's I index) to understand metal relationships and distribution.
Main Results:
- Extremely Randomized Trees showed high performance for Fe, Cr, Zn, Ni, Cu, Co, As, and V.
- Random Forest excelled in predicting Cd and Mn, while Decision Trees were best for Pb.
- Very high Cadmium (Cd) contamination was predicted (CF ≥ 6), with strong positive spatial autocorrelation observed for Cd, Cr, Pb, and As.
Conclusions:
- Machine learning provides a robust framework for predicting heavy metal pollution in Sundarbans sediments.
- Identified specific algorithms for accurate heavy metal prediction, aiding in targeted conservation efforts.
- Findings highlight urgent needs for integrated management and remedial actions to mitigate heavy metal contamination in this vital ecosystem.
