Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF)
The study combined the Positive Matrix Factorization (PMF) receptor model with the Variational Autoencoders (VAE) Machine Learning technique and ecological risk indices to study the spatial distribution, sources and patterns of soil pollution in the study area. 719 soil samples were analysed for sel...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Environmental and Sustainability Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665972725000480 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856641880096768 |
|---|---|
| author | Raymond Webrah Kazapoe Daniel Kwayisi Seidu Alidu Samuel Dzidefo Sagoe Aliyu Ohiani Umaru Ebenezer Ebo Yahans Amuah Millicent Obeng Addai Obed Fiifi Fynn |
| author_facet | Raymond Webrah Kazapoe Daniel Kwayisi Seidu Alidu Samuel Dzidefo Sagoe Aliyu Ohiani Umaru Ebenezer Ebo Yahans Amuah Millicent Obeng Addai Obed Fiifi Fynn |
| author_sort | Raymond Webrah Kazapoe |
| collection | DOAJ |
| description | The study combined the Positive Matrix Factorization (PMF) receptor model with the Variational Autoencoders (VAE) Machine Learning technique and ecological risk indices to study the spatial distribution, sources and patterns of soil pollution in the study area. 719 soil samples were analysed for selected Potentially Toxic Elements (PTEs) concentrations. As (9.68 mg/L), and Pb (7.43 mg/L) reported elevated levels across the area linked to mining activities. The PTEs displayed a decreasing trend in the order Ba > Cr > V > Zn > Cu > Ni > As > Pb > Co. The Pearson correlation matrix outlines two main groups of PTEs: (1) moderate correlation (Ba, Cr, Cu, Ni and V) and (2) weak correlation (As, Pb and Zn). These relationships are corroborated by the VAE, which outlined a low contribution by As and a high contribution by V to all the latent dimensions. The PMF revealed three factors: Factor 1 (geogenic): Ba (77.5%), Cu (54.4%), Ni (66.4%), V (54.0) and Cr (46.8%). Factor 2 (mixed) Co (61.6%), Pb (64.8%) and Zn (71.0%). Factor 3 (anthropogenic) As (86.7%). The degree of contamination analysis depicts that 69.03% of the samples are moderately polluted, while 15.14% and 0.28% revealed considerable and very high pollution, respectively. The pollution load index shows that 20% of the samples depict the existence of pollution. The Potential Ecological Risk Index (RI) values showed that most samples (97.08%) suggest low pollution, while 2.92% depict moderate pollution. Integrating chemometric and machine learning techniques provides a dynamic system that can monitor pollution shifts early, to aid remediation efforts in highly affected areas. |
| format | Article |
| id | doaj-art-1ae8791585a249d6a57dc8d7b9b7770a |
| institution | Kabale University |
| issn | 2665-9727 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environmental and Sustainability Indicators |
| spelling | doaj-art-1ae8791585a249d6a57dc8d7b9b7770a2025-02-12T05:32:47ZengElsevierEnvironmental and Sustainability Indicators2665-97272025-06-0126100627Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF)Raymond Webrah Kazapoe0Daniel Kwayisi1Seidu Alidu2Samuel Dzidefo Sagoe3Aliyu Ohiani Umaru4Ebenezer Ebo Yahans Amuah5Millicent Obeng Addai6Obed Fiifi Fynn7Department of Geological Engineering, University for Development Studies, Nyankpala, GhanaDepartment of Geology, University of Johannesburg, Auckland Park Kingsway Campus, South Africa; Department of Earth Science, University of Ghana, Legon-Accra, Ghana; Corresponding author. Department of Geology, University of Johannesburg, Auckland Park Kingsway Campus, South Africa.Ghana Geological Survey Authority, P.O. Box M80, Accra, GhanaDepartment of Environment and Sustainability Sciences, University for Development Studies, Nyankpala, GhanaDepartment of Geology, University of Maiduguri, Maiduguri, Borno State, NigeriaDepartment of Civil Engineering, Takoradi Technical University, P. O. Box 256, Takoradi, GhanaDepartment of Geography Education, University of Education, Winneba, GhanaDepartment of Environment and Sustainability Sciences, University for Energy and Natural Resources, GhanaThe study combined the Positive Matrix Factorization (PMF) receptor model with the Variational Autoencoders (VAE) Machine Learning technique and ecological risk indices to study the spatial distribution, sources and patterns of soil pollution in the study area. 719 soil samples were analysed for selected Potentially Toxic Elements (PTEs) concentrations. As (9.68 mg/L), and Pb (7.43 mg/L) reported elevated levels across the area linked to mining activities. The PTEs displayed a decreasing trend in the order Ba > Cr > V > Zn > Cu > Ni > As > Pb > Co. The Pearson correlation matrix outlines two main groups of PTEs: (1) moderate correlation (Ba, Cr, Cu, Ni and V) and (2) weak correlation (As, Pb and Zn). These relationships are corroborated by the VAE, which outlined a low contribution by As and a high contribution by V to all the latent dimensions. The PMF revealed three factors: Factor 1 (geogenic): Ba (77.5%), Cu (54.4%), Ni (66.4%), V (54.0) and Cr (46.8%). Factor 2 (mixed) Co (61.6%), Pb (64.8%) and Zn (71.0%). Factor 3 (anthropogenic) As (86.7%). The degree of contamination analysis depicts that 69.03% of the samples are moderately polluted, while 15.14% and 0.28% revealed considerable and very high pollution, respectively. The pollution load index shows that 20% of the samples depict the existence of pollution. The Potential Ecological Risk Index (RI) values showed that most samples (97.08%) suggest low pollution, while 2.92% depict moderate pollution. Integrating chemometric and machine learning techniques provides a dynamic system that can monitor pollution shifts early, to aid remediation efforts in highly affected areas.http://www.sciencedirect.com/science/article/pii/S2665972725000480ToxicityGalamseyGold miningEnvironmental degradationData reduction |
| spellingShingle | Raymond Webrah Kazapoe Daniel Kwayisi Seidu Alidu Samuel Dzidefo Sagoe Aliyu Ohiani Umaru Ebenezer Ebo Yahans Amuah Millicent Obeng Addai Obed Fiifi Fynn Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) Environmental and Sustainability Indicators Toxicity Galamsey Gold mining Environmental degradation Data reduction |
| title | Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) |
| title_full | Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) |
| title_fullStr | Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) |
| title_full_unstemmed | Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) |
| title_short | Advanced analysis of soil pollution in southwestern Ghana using Variational Autoencoders (VAE) and positive matrix factorization (PMF) |
| title_sort | advanced analysis of soil pollution in southwestern ghana using variational autoencoders vae and positive matrix factorization pmf |
| topic | Toxicity Galamsey Gold mining Environmental degradation Data reduction |
| url | http://www.sciencedirect.com/science/article/pii/S2665972725000480 |
| work_keys_str_mv | AT raymondwebrahkazapoe advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT danielkwayisi advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT seidualidu advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT samueldzidefosagoe advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT aliyuohianiumaru advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT ebenezereboyahansamuah advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT millicentobengaddai advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf AT obedfiififynn advancedanalysisofsoilpollutioninsouthwesternghanausingvariationalautoencodersvaeandpositivematrixfactorizationpmf |