Comparison of Ridge and Kernel Ridge Models in Predicting Thermal Stability of Zn-MOF Catalysts DOI Creative Commons
Gustina Alfa Trisnapradika, Muhamad Akrom

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 44 - 48

Published: April 29, 2024

This study investigates machine learning-based quantitative structure-property relationship (QSPR) models for predicting the thermal stability of zinc metal-organic frameworks (Zn-MOF). Utilizing a dataset comprising 151 Zn-MOF compounds with relevant molecular descriptors, ridge (R) and kernel (KR) regression were developed evaluated. The results demonstrate that R model outperforms KR in terms prediction accuracy, exhibiting exceptional performance (R² = 0.999, RMSE 0.0022). While achieving high opportunities further improvement exist through hyperparameter optimization exploration polynomial functions. research underscores potential ML-based QSPR highlights avenues future investigation to enhance accuracy applicability materials science.

Language: Английский

Investigation of Corrosion Inhibition Efficiency of Pyridine-Quinoline Compounds through Machine Learning DOI Creative Commons
Wise Herowati, Muhamad Akrom, Novianto Nur Hidayat

et al.

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 1 - 9

Published: April 29, 2024

Corrosion in materials is a significant concern for the industrial and academic fields because corrosion causes enormous losses various such as economy, environment, society, industry, security, safety, others. Currently, material damage control using organic compounds has become popular field of study. Pyridine quinoline stand out inhibitors among myriad they are non-toxic, inexpensive, effective variety corrosive environments. Experimental investigations developing candidate potential inhibitor time resource-intensive. In this work, we use quantitative structure-property relationship (QSPR)-based machine learning (ML) approach to investigate support vector (SVR), random forest (RF), k-nearest neighbors (KNN) algorithms predictive models inhibition performance. (Inhibition efficiency) pyridine-quinoline derivative on iron. We found that RF model showed best ability based coefficient determination (R2) root mean squared error (RMSE) metrics. Overall, our study provides new insights regarding ML predicting iron surfaces.

Language: Английский

Citations

0
Investigation and Analysis of Influencing Factors of Innovation Quality of Data Science Students Based on Machine Learning DOI
Yingbing Fan,

Lina Sun,

Zhenxu Huang

et al.

Published: April 26, 2024

Language: Английский

Citations

0
Comparison of Ridge and Kernel Ridge Models in Predicting Thermal Stability of Zn-MOF Catalysts DOI Creative Commons
Gustina Alfa Trisnapradika, Muhamad Akrom

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 44 - 48

Published: April 29, 2024

This study investigates machine learning-based quantitative structure-property relationship (QSPR) models for predicting the thermal stability of zinc metal-organic frameworks (Zn-MOF). Utilizing a dataset comprising 151 Zn-MOF compounds with relevant molecular descriptors, ridge (R) and kernel (KR) regression were developed evaluated. The results demonstrate that R model outperforms KR in terms prediction accuracy, exhibiting exceptional performance (R² = 0.999, RMSE 0.0022). While achieving high opportunities further improvement exist through hyperparameter optimization exploration polynomial functions. research underscores potential ML-based QSPR highlights avenues future investigation to enhance accuracy applicability materials science.

Language: Английский

Citations

0