Title: Precise Prediction on the Corrosion Prevention Ability of 1,2,4-Triazole Derivatives: An Artificial Neural Network Approach
Overview:
This record contains the computational dataset, quantitative structure-activity relationship (QSAR) parameters, and artificial neural network (ANN) predictive model metrics evaluating the corrosion inhibition efficiency of 1,2,4-triazole derivatives. Industrial corrosion causes severe environmental contamination and equipment degradation, driving the need for sustainable material protection strategies. This work models complex non-linear relationships between quantum chemical parameters and experimental inhibition efficiency (IE_exp) to provide a rapid, cost-effective screening framework for organic corrosion inhibitors.
Key Predictive Findings: Model Superiority: The proposed ANN framework significantly outperforms traditional non-linear models in predicting inhibitor performance. Correlation Coefficient (R): Increased from 0.888 (conventional non-linear) to 0.967 (ANN). Error Reduction: Mean Square Error (MSE) was reduced from 4.33 × 10^-4 down to 9.81 × 10^-5.
Data & Methodology Details:
The dataset correlates molecular descriptors (HOMO/LUMO energy levels, quantum chemical descriptors, electron transfer indices) of 1,2,4-triazole derivatives with experimentally measured inhibition efficiencies. The ANN configuration eliminates trial-and-error experimental cycles, serving as a scalable machine learning tool for corrosion mitigation in pickling and industrial environments.
Associated Publication:
If you utilize or build upon this dataset or computational model, please cite the published manuscript:Jalgham, R. T. T., Ouchenane, S., Dagdag, O., Ghodbane, H., & Das, H. S. Precise Prediction on the Corrosion Prevention Ability of 1,2,4-Triazole Derivatives: An Artificial Neural Network Approach. ES Energy & Environment.
DOI: https://dx.doi.org/10.30919/esee1344

Ramzi Jalgha

Precise Prediction on the Corrosion Prevention Ability of 1,2,4-