Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds
This study introduces the stacking classical-quantum model (SCQM) as a novel approach to predicting N-heterocyclic compounds' corrosion inhibition efficiency (CIE). SCQM integrates classical models such as Multi-Layer Perceptron Neural Network (MLPNN) and Random Forest (RF) as base learners, wi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Results in Surfaces and Interfaces |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666845925000492 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222495685148672 |
|---|---|
| author | Muhamad Akrom Supriadi Rustad Totok Sutojo Wahyu Aji Eko Prabowo Hermawan Kresno Dipojono Ryo Maezono Hideaki Kasai |
| author_facet | Muhamad Akrom Supriadi Rustad Totok Sutojo Wahyu Aji Eko Prabowo Hermawan Kresno Dipojono Ryo Maezono Hideaki Kasai |
| author_sort | Muhamad Akrom |
| collection | DOAJ |
| description | This study introduces the stacking classical-quantum model (SCQM) as a novel approach to predicting N-heterocyclic compounds' corrosion inhibition efficiency (CIE). SCQM integrates classical models such as Multi-Layer Perceptron Neural Network (MLPNN) and Random Forest (RF) as base learners, with Quantum Neural Network (QNN) as the meta-learner. Experimental results demonstrate SCQM's superior performance with a coefficient of determination (R2) value of 0.98 and root mean squared error (RMSE) of 0.92, outperforming classical models. Predictions of new derivatives PP1 and PP2 yielded CIE values of 95.39% and 94.05%, aligning with experimental results. The novelty lies in the hybrid framework's ability to leverage quantum feature maps, offering a groundbreaking method to explore anti-corrosion materials through quantum machine learning (QML). |
| format | Article |
| id | doaj-art-832c0dfce56c47bbb59f06ae66d9f2ac |
| institution | OA Journals |
| issn | 2666-8459 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Surfaces and Interfaces |
| spelling | doaj-art-832c0dfce56c47bbb59f06ae66d9f2ac2025-08-20T02:06:19ZengElsevierResults in Surfaces and Interfaces2666-84592025-01-011810046210.1016/j.rsurfi.2025.100462Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compoundsMuhamad Akrom0Supriadi Rustad1Totok Sutojo2Wahyu Aji Eko Prabowo3Hermawan Kresno Dipojono4Ryo Maezono5Hideaki Kasai6Research Center for Quantum Computing and Materials Informatics, Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, 50131, Indonesia; Corresponding author.Research Center for Quantum Computing and Materials Informatics, Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, 50131, Indonesia; Corresponding author.Research Center for Quantum Computing and Materials Informatics, Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, 50131, IndonesiaResearch Center for Quantum Computing and Materials Informatics, Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, 50131, IndonesiaQuantum and Nano Technologies Research Group, Faculty of Industrial Technology, Institut Teknologi Bandung, Bandung, 40132, Indonesia; Corresponding author.School of Information Science, Japan Advanced Institute of Science and Technology, Ishikawa, 923-1292, JapanDepartment of Applied Physics, Osaka University, Suita, Osaka, 565-0871, JapanThis study introduces the stacking classical-quantum model (SCQM) as a novel approach to predicting N-heterocyclic compounds' corrosion inhibition efficiency (CIE). SCQM integrates classical models such as Multi-Layer Perceptron Neural Network (MLPNN) and Random Forest (RF) as base learners, with Quantum Neural Network (QNN) as the meta-learner. Experimental results demonstrate SCQM's superior performance with a coefficient of determination (R2) value of 0.98 and root mean squared error (RMSE) of 0.92, outperforming classical models. Predictions of new derivatives PP1 and PP2 yielded CIE values of 95.39% and 94.05%, aligning with experimental results. The novelty lies in the hybrid framework's ability to leverage quantum feature maps, offering a groundbreaking method to explore anti-corrosion materials through quantum machine learning (QML).http://www.sciencedirect.com/science/article/pii/S2666845925000492Stacking modelQuantum machine learningCorrosion inhibitionN-heterocyclic |
| spellingShingle | Muhamad Akrom Supriadi Rustad Totok Sutojo Wahyu Aji Eko Prabowo Hermawan Kresno Dipojono Ryo Maezono Hideaki Kasai Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds Results in Surfaces and Interfaces Stacking model Quantum machine learning Corrosion inhibition N-heterocyclic |
| title | Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds |
| title_full | Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds |
| title_fullStr | Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds |
| title_full_unstemmed | Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds |
| title_short | Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds |
| title_sort | stacking classical quantum hybrid learning approach for corrosion inhibition efficiency of n heterocyclic compounds |
| topic | Stacking model Quantum machine learning Corrosion inhibition N-heterocyclic |
| url | http://www.sciencedirect.com/science/article/pii/S2666845925000492 |
| work_keys_str_mv | AT muhamadakrom stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT supriadirustad stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT totoksutojo stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT wahyuajiekoprabowo stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT hermawankresnodipojono stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT ryomaezono stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds AT hideakikasai stackingclassicalquantumhybridlearningapproachforcorrosioninhibitionefficiencyofnheterocycliccompounds |