Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO
The retention of polar pharmaceutical active compounds (PPhACs) by nanofiltration and reverse osmosis (NF/RO) membranes is of paramount importance in membrane separation processes. The retention of 21 PPhACs was correlated using artificial intelligence techniques: multi-layer perceptron (MLP), feedf...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Society of Chemical Engineers
2023-11-01
|
| Series: | Kemija u Industriji |
| Subjects: | |
| Online Access: | http://silverstripe.fkit.hr/kui/assets/Uploads/1-617-626-KUI-11-12-2023.pdf |
| _version_ | 1797516730854014976 |
|---|---|
| author | Yamina Ammi Cherif Si-Moussa Salah Hanini |
| author_facet | Yamina Ammi Cherif Si-Moussa Salah Hanini |
| author_sort | Yamina Ammi |
| collection | DOAJ |
| description | The retention of polar pharmaceutical active compounds (PPhACs) by nanofiltration and reverse osmosis (NF/RO) membranes is of paramount importance in membrane separation processes. The retention of 21 PPhACs was correlated using artificial intelligence techniques: multi-layer perceptron (MLP), feedforward neural network with radial basis function (RBF), and support vector machine (SVM). A database of 541 retention values has been collected from the literature. The results showed a high predictive capacity of the MLP model for the retention of PPhACs by NF/RO with a very high correlation coefficient (R = 0.9714) and a very low root mean squared error (RMSE = 3.9139 %) for the entire data set. The comparison between the three models showed the superiority of the MLP model. The sensitivity analysis emphasised that the retention of PPhACs is governed by three interactions arranged in descending order: polarity interactions (hydrophobicity/hydrophilicity), electrostatic repulsion, and steric hindrance. This research suggests that the PPhACs retention on the NF/RO membrane strongly depends on the topological polar surface area. |
| first_indexed | 2024-03-10T07:04:57Z |
| format | Article |
| id | doaj.art-992f141517044553bf7399c92d73f408 |
| institution | Directory Open Access Journal |
| issn | 0022-9830 1334-9090 |
| language | English |
| last_indexed | 2024-03-10T07:04:57Z |
| publishDate | 2023-11-01 |
| publisher | Croatian Society of Chemical Engineers |
| record_format | Article |
| series | Kemija u Industriji |
| spelling | doaj.art-992f141517044553bf7399c92d73f4082023-11-22T15:54:37ZengCroatian Society of Chemical EngineersKemija u Industriji0022-98301334-90902023-11-017211-1261762610.15255/KUI.2022.085Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/ROYamina Ammi0Cherif Si-Moussa1Salah Hanini2Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, AlgeriaLaboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, AlgeriaLaboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, AlgeriaThe retention of polar pharmaceutical active compounds (PPhACs) by nanofiltration and reverse osmosis (NF/RO) membranes is of paramount importance in membrane separation processes. The retention of 21 PPhACs was correlated using artificial intelligence techniques: multi-layer perceptron (MLP), feedforward neural network with radial basis function (RBF), and support vector machine (SVM). A database of 541 retention values has been collected from the literature. The results showed a high predictive capacity of the MLP model for the retention of PPhACs by NF/RO with a very high correlation coefficient (R = 0.9714) and a very low root mean squared error (RMSE = 3.9139 %) for the entire data set. The comparison between the three models showed the superiority of the MLP model. The sensitivity analysis emphasised that the retention of PPhACs is governed by three interactions arranged in descending order: polarity interactions (hydrophobicity/hydrophilicity), electrostatic repulsion, and steric hindrance. This research suggests that the PPhACs retention on the NF/RO membrane strongly depends on the topological polar surface area.http://silverstripe.fkit.hr/kui/assets/Uploads/1-617-626-KUI-11-12-2023.pdfmachine learningneural networksmodellingretentionpphacsnanofiltrationreverse osmosis |
| spellingShingle | Yamina Ammi Cherif Si-Moussa Salah Hanini Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO Kemija u Industriji machine learning neural networks modelling retention pphacs nanofiltration reverse osmosis |
| title | Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO |
| title_full | Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO |
| title_fullStr | Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO |
| title_full_unstemmed | Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO |
| title_short | Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO |
| title_sort | machine learning and neural networks for modelling the retention of pphacs by nf ro |
| topic | machine learning neural networks modelling retention pphacs nanofiltration reverse osmosis |
| url | http://silverstripe.fkit.hr/kui/assets/Uploads/1-617-626-KUI-11-12-2023.pdf |
| work_keys_str_mv | AT yaminaammi machinelearningandneuralnetworksformodellingtheretentionofpphacsbynfro AT cherifsimoussa machinelearningandneuralnetworksformodellingtheretentionofpphacsbynfro AT salahhanini machinelearningandneuralnetworksformodellingtheretentionofpphacsbynfro |