Stacking classical-quantum hybrid learning approach for corrosion inhibition efficiency of N-heterocyclic compounds

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhamad Akrom, Supriadi Rustad, Totok Sutojo, Wahyu Aji Eko Prabowo, Hermawan Kresno Dipojono, Ryo Maezono, Hideaki Kasai
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Results in Surfaces and Interfaces
Subjects:
Stacking model
Quantum machine learning
Corrosion inhibition
N-heterocyclic
Online Access:http://www.sciencedirect.com/science/article/pii/S2666845925000492
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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).
ISSN:2666-8459

Similar Items