Home > Research > Publications & Outputs > A Hybrid Machine Learning Approach to Predict a...

Research

Links

Text available via DOI:

Keywords

View graph of relations

A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ

Research output: Contribution to Journal/Magazine › Journal article › peer-review

E-pub ahead of print

Standard

A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ. / Wang, Yong; Ma, Xudong; Robson, Alexander J. et al.
In: Plasma Processes Polym., 11.05.2025.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Wang, Y, Ma, X, Robson, AJ, Short, RD & Bradley, JW 2025, 'A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ', Plasma Processes Polym. https://doi.org/10.1002/ppap.70035

APA

Wang, Y., Ma, X., Robson, A. J., Short, R. D., & Bradley, J. W. (2025). A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ. Plasma Processes Polym., Article e70035. Advance online publication. https://doi.org/10.1002/ppap.70035

Vancouver

Wang Y, Ma X, Robson AJ, Short RD, Bradley JW. A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ. Plasma Processes Polym. 2025 May 11;e70035. Epub 2025 May 11. doi: 10.1002/ppap.70035

Author

Wang, Yong ; Ma, Xudong ; Robson, Alexander J. et al. / A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ. In: Plasma Processes Polym. 2025.

Bibtex

@article{08d7a20c12d4437997223576fc4b5aa2,
title = "A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ",
abstract = "We developed a hybrid machine learning model, integrating Artificial Neural Network (ANN), Random Forest (RF) and AdaBoost (AB), to predict and evaluate the plasma polymerization process of TEMPO monomer, specifically for Nitric Oxide films. This model is specifically designed to adeptly navigate the intricate landscape of the plasma polymerization process. Through genetic algorithm optimization, we have fine‐tuned our hybrid model's algorithm weights, achieving results that closely match experimental data. TEMPO‐Helium flow ratio is identified as the most critical parameter for the surface N percentage, with a relative importance of 41%. Frequency has the greatest influence on the N‐O percentage, with a relative importance of 30%. The intertwined influence of different polymerization parameters on the film's surface chemistry has been detailed.",
keywords = "films, deep learning, machine learning, plasma polymerization, TEMPO",
author = "Yong Wang and Xudong Ma and Robson, {Alexander J.} and Short, {Robert D.} and Bradley, {James W.}",
year = "2025",
month = may,
day = "11",
doi = "10.1002/ppap.70035",
language = "English",
journal = "Plasma Processes Polym.",
issn = "1612-8850",
publisher = "Wiley-VCH Verlag",

}

RIS

TY - JOUR

T1 - A Hybrid Machine Learning Approach to Predict and Evaluate Surface Chemistries of Films Deposited via APPJ

AU - Wang, Yong

AU - Ma, Xudong

AU - Robson, Alexander J.

AU - Short, Robert D.

AU - Bradley, James W.

PY - 2025/5/11

Y1 - 2025/5/11

N2 - We developed a hybrid machine learning model, integrating Artificial Neural Network (ANN), Random Forest (RF) and AdaBoost (AB), to predict and evaluate the plasma polymerization process of TEMPO monomer, specifically for Nitric Oxide films. This model is specifically designed to adeptly navigate the intricate landscape of the plasma polymerization process. Through genetic algorithm optimization, we have fine‐tuned our hybrid model's algorithm weights, achieving results that closely match experimental data. TEMPO‐Helium flow ratio is identified as the most critical parameter for the surface N percentage, with a relative importance of 41%. Frequency has the greatest influence on the N‐O percentage, with a relative importance of 30%. The intertwined influence of different polymerization parameters on the film's surface chemistry has been detailed.

AB - We developed a hybrid machine learning model, integrating Artificial Neural Network (ANN), Random Forest (RF) and AdaBoost (AB), to predict and evaluate the plasma polymerization process of TEMPO monomer, specifically for Nitric Oxide films. This model is specifically designed to adeptly navigate the intricate landscape of the plasma polymerization process. Through genetic algorithm optimization, we have fine‐tuned our hybrid model's algorithm weights, achieving results that closely match experimental data. TEMPO‐Helium flow ratio is identified as the most critical parameter for the surface N percentage, with a relative importance of 41%. Frequency has the greatest influence on the N‐O percentage, with a relative importance of 30%. The intertwined influence of different polymerization parameters on the film's surface chemistry has been detailed.

KW - films

KW - deep learning

KW - machine learning

KW - plasma polymerization

KW - TEMPO

U2 - 10.1002/ppap.70035

DO - 10.1002/ppap.70035

M3 - Journal article

JO - Plasma Processes Polym.

JF - Plasma Processes Polym.

SN - 1612-8850

M1 - e70035

ER -