Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 9 min ago
Peer-reviewedCC BYiScience

Machine learning-driven prediction of heavy metal pollution for aquatic health surveillance and disease control

  • Md. Abdullah Al Mamun Hridoy1
  • Pakorn Ditthakit2
  • Akib Hosen3
  • Mohd. Saifur Rahman4
  • Minhaj Uddin5
  • Kamrul Hasan6
  • Yeaman Hossain4
  • Chiara Bordin7
  • Leonardo Goliatt8
  • Md. Abdullah Al Mamun9,10
  • Paolo Pastorino11
11 affiliations
  1. 1Faculty of Fisheries, Sylhet Agricultural University, Sylhet 3100, Bangladesh
  2. 2Center of Excellence in Sustainable Disaster Management, School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80161, Thailand
  3. 3Department of Environmental Science, Bangladesh Agricultural University, Mymensingh 2202, Bangladesh
  4. 4Department of Agricultural Construction and Environmental Engineering, Sylhet Agricultural University, Sylhet 3100, Bangladesh
  5. 5Department of Agricultural and Biological Engineering, Mississippi State University, 130 Creelman Street, Mississippi State, MS 39762, USA
  6. 6Faculty of Agricultural Economics and Business Studies, Sylhet Agricultural University, Sylhet 3100, Bangladesh
  7. 7Department of Computer Science, UiT The Arctic University of Norway, 6050, Langnes, 9037 Tromsø, Norway
  8. 8Department of Computational and Applied Mechanics, Federal University of Juiz de Fora, Juiz de Fora 36036-900, Brazil
  9. 9Department of Fish Health Management, Laboratory of Fish Diseases Diagnosis and Pharmacology, Faculty of Fisheries, Sylhet Agricultural University, Sylhet, Bangladesh
  10. 10Faculty of Veterinary Medicine, Universitas Brawijaya, Malang, East Java, 65151, Indonesia
  11. 11Experimental Zooprophylactic Institute of Piedmont, Liguria and Aosta Valley, Via Bologna 148, 10154 Turin, Italy
Open at sourceDOICite

Abstract

Heavy metal (HM) accumulation in lake sediments poses ecological risks and may increase aquatic organism vulnerability to disease, requiring cost-effective monitoring tools. This study developed an interpretable multi-output machine learning (ML) framework to predict sediment HMs (As, Cd, Cu, Hg, Ni, Pb, and Zn) in Swan Lake, using field variables (pH, dissolved oxygen, and temperature), sediment texture (median grain size), and aluminum content (Al%). Models with nested preprocessing and cross-validation achieved strong performance (R 2 = 0.824–0.997). Optimal algorithms varied by metal, while random forest showed the most consistent results, balancing accuracy, low error, and robustness to outliers. Predicted concentrations were integrated with ecological risk indices (Igeo, PLI, and Hakanson RI), indicating low pollution with localized Zn hotspots. Explainability analysis identified pH and Al% as key drivers, supporting ML-based screening for aquatic monitoring and early warning systems.

Related

  1. Hybrid stacked bidirectional deep learning with attention based air pollution prediction for environmental sustainability
    Zhang Wei, Pushpa Vinu Amalraj
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossref
  2. Impacts of Combined Microplastics and Heavy Metal Pollution on Aquatic Ecological Health: Insights from Trophic Levels.
    Haicheng Liu, Huixuan Xu, Chenxuan Rao
    ToxicsPeer-reviewedCC BYFull textEnvironmental science & pollutionEurope PMC
  3. Machine-learning prediction of freezing temperature in Pb-contaminated soils remediated with biochar
    Laila Safi
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossref
  4. FastNet: Improving the Physical Consistency of Machine Learning Weather Prediction Models through Loss Function Design
    Tom Dunstan, Oliver Strickson, Thusal Bennett +34
    Artificial Intelligence for the Earth SystemsPeer-reviewedLicence not statedFull text10 citedAtmospheric science & meteorologyOpenAlex
  5. AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning
    Ewan Pinnington, Peter Lean, Mihai Alexe +8
    arXiv (Cornell University)PreprintCC BY-NC-NDFull text8 citedAtmospheric science & meteorologyOpenAlex

Cite

BibTeXRIS
BibTeX
@article{hridoy2026machine,
  title = {{Machine learning-driven prediction of heavy metal pollution for aquatic health surveillance and disease control}},
  author = {Md. Abdullah Al Mamun Hridoy and Pakorn Ditthakit and Akib Hosen and Mohd. Saifur Rahman and Minhaj Uddin and Kamrul Hasan and Yeaman Hossain and Chiara Bordin and Leonardo Goliatt and Md. Abdullah Al Mamun and Paolo Pastorino},
  journal = {iScience},
  year = {2026},
  month = jul,
  doi = {10.1016/j.isci.2026.116549},
  url = {https://doi.org/10.1016/j.isci.2026.116549},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Machine learning-driven prediction of heavy metal pollution for aquatic health surveillance and disease control
AU  - Md. Abdullah Al Mamun Hridoy
AU  - Pakorn Ditthakit
AU  - Akib Hosen
AU  - Mohd. Saifur Rahman
AU  - Minhaj Uddin
AU  - Kamrul Hasan
AU  - Yeaman Hossain
AU  - Chiara Bordin
AU  - Leonardo Goliatt
AU  - Md. Abdullah Al Mamun
AU  - Paolo Pastorino
PY  - 2026
DA  - 2026/07/01
JO  - iScience
DO  - 10.1016/j.isci.2026.116549
UR  - https://doi.org/10.1016/j.isci.2026.116549
AB  - Heavy metal (HM) accumulation in lake sediments poses ecological risks and may increase aquatic organism vulnerability to disease, requiring cost-effective monitoring tools. This study developed an interpretable multi-output machine learning (ML) framework to predict sediment HMs (As, Cd, Cu, Hg, Ni, Pb, and Zn) in Swan Lake, using field variables (pH, dissolved oxygen, and temperature), sediment texture (median grain size), and aluminum content (Al%). Models with nested preprocessing and cross-validation achieved strong performance (R 2 = 0.824–0.997). Optimal algorithms varied by metal, while random forest showed the most consistent results, balancing accuracy, low error, and robustness to outliers. Predicted concentrations were integrated with ecological risk indices (Igeo, PLI, and Hakanson RI), indicating low pollution with localized Zn hotspots. Explainability analysis identified pH and Al% as key drivers, supporting ML-based screening for aquatic monitoring and early warning systems.
SN  - 2589-0042
ER  -