EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI for Material Property Prediction Based on Energy Cloud: A Shapley-Driven Approach

Faiza Qayyum iD, Murad Ali Khan, Do-Hyeun Kim, Hyunseok Ko iD, Ga-Ae Ryu

Materials · 24.11.2023 · 16 (23) · 7322

DOI: 10.3390/ma16237322 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 24.11.2023. Verfasst von Faiza Qayyum und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Jeju National University, Jeju-si 63243, Republic of Korea. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF), Virtual Engineering Platform Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The scientific community has raised increasing apprehensions over the transparency and interpretability of machine learning models employed in various domains, particularly in the field of materials science. The intrinsic intricacy of these models frequently results in their characterization as “black boxes”, which poses a difficulty in emphasizing the significance of producing lucid and readily understandable model outputs. In addition, the assessment of model performance requires careful deliberation of several essential factors. The objective of this study is to utilize a deep learning framework called TabNet to predict lead zirconate titanate (PZT) ceramics’ dielectric constant property by employing their components and processes. By recognizing the crucial importance of predicting PZT properties, this research seeks to enhance the comprehension of the results generated by the model and gain insights into the association between the model and predictor variables using various input parameters. To achieve this, we undertake a thorough analysis with Shapley additive explanations (SHAP). In order to enhance the reliability of the prediction model, a variety of cross-validation procedures are utilized. The study demonstrates that the TabNet model significantly outperforms traditional machine learning models in predicting ceramic characteristics of PZT components, achieving a mean squared error (MSE) of 0.047 and a mean absolute error (MAE) of 0.042. Key contributing factors, such as d33, tangent loss, and chemical formula, are identified using SHAP plots, highlighting their importance in predictive analysis. Interestingly, process time is less effective in predicting the dielectric constant. This research holds considerable potential for advancing materials discovery and predictive systems in PZT ceramics, offering deep insights into the roles of various parameters.

Schlagwörter

Stichwörter der Autor:innen

ShapelyTabNetceramicdeep learningexplainable artificial intelligencemachine learningmaterial

Autor:innen und Institutionen

  • Department of Computer Engineering, Jeju National University, Jeju-si 63243, Republic of Korea.
  • Center of Materials Digitalization, Korea Institute of Ceramic Engineering and Technology, Jinju-si 52851, Republic of Korea.

ORCID-Profile: Faiza Qayyum, Hyunseok Ko

Förderung

  • National Research Foundation of Korea (NRF)
  • Virtual Engineering Platform Project

Zitieren

APA

Qayyum, F., Khan, M. A., Kim, D. H., Ko, H., & Ryu, G. A. (2023). Explainable AI for Material Property Prediction Based on Energy Cloud: A Shapley-Driven Approach. Materials, 16(23), 7322. https://doi.org/10.3390/ma16237322

Vancouver

Qayyum F, Khan MA, Kim DH, Ko H, Ryu GA. Explainable AI for Material Property Prediction Based on Energy Cloud: A Shapley-Driven Approach. Materials. 2023;16(23):7322. doi:10.3390/ma16237322

BibTeX
@article{Qayyum2023,
  author = {Qayyum, Faiza and Khan, Murad Ali and Kim, Do-Hyeun and Ko, Hyunseok and Ryu, Ga-Ae},
  title = {Explainable AI for Material Property Prediction Based on Energy Cloud: A Shapley-Driven Approach},
  journal = {Materials},
  year = {2023},
  volume = {16},
  number = {23},
  pages = {7322},
  doi = {10.3390/ma16237322}
}
Kostenlos starten →