Integrating machine learning and multi-linear regression modeling approaches in groundwater quality assessment around Obosi, SE Nigeria

Akakuru, Obinna Chigoziem; Akaolisa, Casmir C Zanders; Aigbadon, Godwin Okumagbe; Eyankware, Moses Oghenenyoreme; Opara, Alexander Iheanyichukwu; Obasi, P. N.; Ofoh, Ifeyinwa Juliana; Njoku, Adaora Olivia; Akudinobi, B. E. B.

doi:10.1007/s10668-022-02679-8

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article4

Book1

Relationship

Self Cite1

Independent4

Authors

Journals

Cited by 13 publications

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Leveraging the Power of AI for Sustainable Oceans

Gupta,

Tanwar

2024

The Springer Series in Applied Machine Learning

View full text Add to dashboard Cite

Leveraging the Power of AI for Sustainable Oceans

Gupta,

Tanwar

2024

The Springer Series in Applied Machine Learning

View full text Add to dashboard Cite

Non-carcinogenic health risk assessment and predicting of pollution indexing of groundwater around Osisioma, Nigeria, using artificial neural networks and multi-linear modeling principles

Akakuru

Njoku²,

Obinna-Akakuru³

et al. 2023

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

Non-carcinogenic health risk assessment and predicting of organic and heavy metal pollution of groundwater around Osisioma, Nigeria, using Artificial Neural Networks and Multi-Linear Modeling Principles has been done. 30 groundwater samples were collected systematically and analyzed for organic and heavy metal pollutants. The results of the analysis showed that the heavy metals and organic pollutants within the study area contributed to the pollution of groundwater resources in the locality. However, copper, ethylbenzene, xylene and toluene were within the recommended standard, whereas arsenic, iron, chromium, lead, and benzene were above the recommended standard for drinking water. Correlation matrix and principal component analysis assessment indicated weak correlation and that organic pollutants were major contributors to the loadings. The Contamination factor, Pollution load index, Metal pollution index, Geoaccumulation index, Potential ecological risk index, Elemental Contamination Index, and overall Metal Contamination Index showed no significant pollution, whereas the Heavy Metal Evaluation Index, Pollution Index of Groundwater results showed worrisome impact of the anthropogenic activities on the groundwater quality. Health risk assessment showed that children are more at risk than adults as it related to taking polluted water. MLR models performed better than the ANN. Seven (7) mathematical models were generated for the prediction of pollution indices. Based on the results, this study recommends regular monitoring of groundwater resources and the integration of ANN and MLR modeling approaches for the prediction of pollution indices.

show abstract