Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network
The quick identification of heavy metals is of major importance and is beneficial for controlling the fertilizer production process in the fertilizer industries. This work aimed to use visible and near-infrared spectroscopy (Vis-NIR), Boruta, and deep learning to establish rapid heavy metals screeni...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/c0243264553c40a0944fe46f6f82ae52 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:c0243264553c40a0944fe46f6f82ae52 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:c0243264553c40a0944fe46f6f82ae522021-11-22T04:16:37ZPotential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network0147-651310.1016/j.ecoenv.2021.112996https://doaj.org/article/c0243264553c40a0944fe46f6f82ae522021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S0147651321011088https://doaj.org/toc/0147-6513The quick identification of heavy metals is of major importance and is beneficial for controlling the fertilizer production process in the fertilizer industries. This work aimed to use visible and near-infrared spectroscopy (Vis-NIR), Boruta, and deep learning to establish rapid heavy metals screening methods. Boruta algorithm was used to extract appropriate wavelengths, and a deep belief network (DBN) was computed to determine the amounts of various heavy metals such as chromium (Cr), cadmium (Cd), lead (Pb), and mercury (Hg) for both the entire and selected wavelengths. To assess the model, coefficient of determination (R2), root mean squared error (RMSE), and residual prediction deviation (RPD) were used to calculate the reliability of the model. The results of the selected wavelengths were excellent and much higher than the full wavelengths with R2p = 0.96, RMSEP = 0.2017 mg kg-1 and RPDpred = 5.0 for Cr; R2p = 0.91, RMSEP = 0.2832 mg kg-1 and RPDpred = 3.4 for Pb; R2p = 0.90, RMSEP = 0.2992 mg kg-1, and RPDpred = 3.3 for Hg. Descent prediction was obtained also for Cd (R2p = 0.87, RMSEP = 0.3435 mg kg-1, and RPDpred = 2.7). To further assess the robustness of the DBN, it was compared with conventional machine learning methods such as support vector machine for regression (SVR), k nearest neighbor (KNN), and partial least squares (PLS). The overall results indicated that the Vis-NIR technique coupled with Boruta and DBN could be reliable and accurate for screening heavy metals in organic fertilizers.Mahamed Lamine GuindoMuhammad Hilal KabirRongqin ChenFei LiuElsevierarticleOrganic fertilizerVis-NIRHeavy-metalsBorutaDeep belief networkEnvironmental pollutionTD172-193.5Environmental sciencesGE1-350ENEcotoxicology and Environmental Safety, Vol 228, Iss , Pp 112996- (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Organic fertilizer Vis-NIR Heavy-metals Boruta Deep belief network Environmental pollution TD172-193.5 Environmental sciences GE1-350 |
spellingShingle |
Organic fertilizer Vis-NIR Heavy-metals Boruta Deep belief network Environmental pollution TD172-193.5 Environmental sciences GE1-350 Mahamed Lamine Guindo Muhammad Hilal Kabir Rongqin Chen Fei Liu Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
description |
The quick identification of heavy metals is of major importance and is beneficial for controlling the fertilizer production process in the fertilizer industries. This work aimed to use visible and near-infrared spectroscopy (Vis-NIR), Boruta, and deep learning to establish rapid heavy metals screening methods. Boruta algorithm was used to extract appropriate wavelengths, and a deep belief network (DBN) was computed to determine the amounts of various heavy metals such as chromium (Cr), cadmium (Cd), lead (Pb), and mercury (Hg) for both the entire and selected wavelengths. To assess the model, coefficient of determination (R2), root mean squared error (RMSE), and residual prediction deviation (RPD) were used to calculate the reliability of the model. The results of the selected wavelengths were excellent and much higher than the full wavelengths with R2p = 0.96, RMSEP = 0.2017 mg kg-1 and RPDpred = 5.0 for Cr; R2p = 0.91, RMSEP = 0.2832 mg kg-1 and RPDpred = 3.4 for Pb; R2p = 0.90, RMSEP = 0.2992 mg kg-1, and RPDpred = 3.3 for Hg. Descent prediction was obtained also for Cd (R2p = 0.87, RMSEP = 0.3435 mg kg-1, and RPDpred = 2.7). To further assess the robustness of the DBN, it was compared with conventional machine learning methods such as support vector machine for regression (SVR), k nearest neighbor (KNN), and partial least squares (PLS). The overall results indicated that the Vis-NIR technique coupled with Boruta and DBN could be reliable and accurate for screening heavy metals in organic fertilizers. |
format |
article |
author |
Mahamed Lamine Guindo Muhammad Hilal Kabir Rongqin Chen Fei Liu |
author_facet |
Mahamed Lamine Guindo Muhammad Hilal Kabir Rongqin Chen Fei Liu |
author_sort |
Mahamed Lamine Guindo |
title |
Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
title_short |
Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
title_full |
Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
title_fullStr |
Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
title_full_unstemmed |
Potential of Vis-NIR to measure heavy metals in different varieties of organic-fertilizers using Boruta and deep belief network |
title_sort |
potential of vis-nir to measure heavy metals in different varieties of organic-fertilizers using boruta and deep belief network |
publisher |
Elsevier |
publishDate |
2021 |
url |
https://doaj.org/article/c0243264553c40a0944fe46f6f82ae52 |
work_keys_str_mv |
AT mahamedlamineguindo potentialofvisnirtomeasureheavymetalsindifferentvarietiesoforganicfertilizersusingborutaanddeepbeliefnetwork AT muhammadhilalkabir potentialofvisnirtomeasureheavymetalsindifferentvarietiesoforganicfertilizersusingborutaanddeepbeliefnetwork AT rongqinchen potentialofvisnirtomeasureheavymetalsindifferentvarietiesoforganicfertilizersusingborutaanddeepbeliefnetwork AT feiliu potentialofvisnirtomeasureheavymetalsindifferentvarietiesoforganicfertilizersusingborutaanddeepbeliefnetwork |
_version_ |
1718418246223265792 |