A Transfer Learning‐Based Method for Facilitating the Prediction of Unsteady Crystal Growth
- 3 July 2022
- journal article
- research article
- Published by Wiley in Advanced Theory and Simulations
- Vol. 5 (9)
Abstract
Real‐time prediction and dynamic control systems that can adapt to an unsteady environment are necessary for material fabrication processes, especially crystal growth. Recent studies have demonstrated the effectiveness of machine learning in predicting an unsteady crystal growth process, but its wider application is hindered by the large amount of training data required for sufficient accuracy. To address this problem, this study investigates the capability of transfer learning to predict geometric evolution in an unsteady silicon carbide (SiC) solution growth system based on a small amount of data. The performance of transferred models is discussed regarding the effect of the transfer learning method, training data amount, and time step length. The transfer learning strategy yields the same accuracy as that of training from scratch but requires only 20% of the training data. The accuracy is stably inherited through successive time steps, which demonstrates the effectiveness of transfer learning in reducing the required amount of training data for predicting evolution in an unsteady crystal growth process. Moreover, the transferred models trained with relatively more data (no more than 100%) further improve the accuracy inherited from the source model through multiple time steps, which broadens the application scope of transfer learning.Keywords
Funding Information
- New Energy and Industrial Technology Development Organization (JPNP20006)
- Japan Society for the Promotion of Science (JP18H03839)
This publication has 34 references indexed in Scilit:
- Optimization of magnetically driven directional solidification of silicon using artificial neural networks and Gaussian process modelsJournal of Crystal Growth, 2017
- Machine Learning Energies of 2 Million ElpasoliteCrystalsPhysical Review Letters, 2016
- A survey of transfer learningJournal of Big Data, 2016
- Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniquesPhysical Review B, 2016
- Optimization via simulation of a seeded directional solidification process for quasi-single crystalline silicon ingots by insulation partition designJournal of Crystal Growth, 2014
- Dynamic simulation of impurity transport and chemical reactions in a Bridgman furnace for directional solidification of multi-crystalline siliconJournal of Crystal Growth, 2013
- Optimization of the parameters affecting the shape and position of crystal–melt interface in YAG single crystal growthJournal of Crystal Growth, 2009
- Transient temperature phenomena during sublimation growth of silicon carbide single crystalsJournal of Crystal Growth, 2003
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Experimental and numerical study of the VGF growth of CdTe crystalJournal of Crystal Growth, 2002