2022
DOI: 10.1016/j.mtcomm.2022.103163
|View full text |Cite
|
Sign up to set email alerts
|

Development of QSAR-based (MLR/ANN) predictive models for effective design of pyridazine corrosion inhibitors

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0
2

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 39 publications
(29 citation statements)
references
References 54 publications
0
13
0
2
Order By: Relevance
“…Specifically, the utilization of the GB algorithm in conjunction with cheminformatics-derived descriptors selected by the PFI method outperforms the performance achieved by employing the NN algorithm with quantum chemically-derived descriptors and adsorption energies on the PQ-41 dataset. 13 This superior performance extends to comparisons with the NN algorithm combined with five selected quantum chemically-derived and cheminformatics-derived descriptors on the P-20 and IL-30 datasets, 14,15 as well as the integration of deep learning models, such as DMPNN, with cheminformatics-derived descriptors on the CO-270 dataset. 17…”
Section: Resultsmentioning
confidence: 87%
“…Specifically, the utilization of the GB algorithm in conjunction with cheminformatics-derived descriptors selected by the PFI method outperforms the performance achieved by employing the NN algorithm with quantum chemically-derived descriptors and adsorption energies on the PQ-41 dataset. 13 This superior performance extends to comparisons with the NN algorithm combined with five selected quantum chemically-derived and cheminformatics-derived descriptors on the P-20 and IL-30 datasets, 14,15 as well as the integration of deep learning models, such as DMPNN, with cheminformatics-derived descriptors on the CO-270 dataset. 17…”
Section: Resultsmentioning
confidence: 87%
“…Deskriptor kimia kuantum dari inhibitor merupakan faktor kunci dalam penghambatan korosi. Penghambatan korosi sangat bergantung pada reaktivitas kimiawi dari molekul inhibitor yang direpresentasikan dalam beragam deskriptor kimia kuantum [17], [18], [21]. Deskriptor kimia kuantum yang umumnya digunakan sebagai fitur dalam dataset untuk mengevaluasi korelasinya terhadap efisiensi inhibisi korosi diantaranya energi HOMO, energi LUMO, energi gap (∆E), potensial ionisasi (I), afinitas elektron (A), global hardness (η), global softness (σ), elektronegativitas (χ), momen dipol (μ), elektrofilisitas (ω), fraksi elektron yang ditransfer (∆N), energi total (TE), dan lain-lainnya.…”
Section: Dataset Fitur Dan Targetunclassified
“…Model prediksi yang baik ditunjukkan oleh nilai RMSE yang rendah dan R 2 yang mendekati 1. Metrik kesalahan statistik ini digunakan untuk menilai keakuratan model, dimana kesalahan statistik yang lebih rendah menunjukkan prediktabilitas model yang lebih baik [18], [27].…”
Section: Konsep Perancanganunclassified
“…The majority of inhibitor defense is based on the adsorption of inhibitor molecules on metal surfaces, followed by the creation of a protective layer [25,26]. Quantitative structure-activity relationships have been studied, and the relation between the chemical structure of compounds and their inhibition efficiencies toward corrosion of different metal surfaces were reported [27][28][29][30][31][32][33]. Many corrosion inhibitors used in operation were natural products derived from plant parts such as roots, bark, seeds, stems, leaves, flowers, and fruits [34][35][36][37].…”
Section: Introductionmentioning
confidence: 99%