Development of quantum machine learning to evaluate the corrosion inhibition capability of pyrimidine compounds

Abstract

This investigation employs a quantum neural network (QNN) synergistically integrated with a quantitative structure-property relationship (QSPR) model for the comprehensive evaluation of corrosion inhibition efficiency (CIE) in pyrimidine compounds. The QNN, exhibiting superior performance over conventional methodologies, attains commendable predictive precision, as evidenced by metrics: R2 = 0.981, RMSE = 0.53, MAE = 0.43, and MAD = 0.42. The prognosticated CIE values for the synthesized derivatives (P1, P2, P3) are 91.17, 98.69, and 99.21, respectively. This pioneering approach holds promise for a transformative impact on both the manufacturing and evaluation procedures associated with novel anti-corrosion materials.