Merits and Demerits of Machine Learning of Ferroelectric, Flexoelectric, and Electrolytic Properties of Ceramic Materials
Author:
Open Access
Abstract
In the present review, the merits and demerits of machine learning (ML) in materials science are discussed, compared with first principles calculations (PDE (partial differential equations) model) and physical or phenomenological ODE (ordinary differential equations) model calculations. ML is basically a fitting procedure of pre-existing (experimental) data as a function of various factors called descriptors. If excellent descriptors can be selected and the training data contain negligible error, the predictive power of a ML model is relatively high. However, it is currently very difficult for a ML model to predict experimental results beyond the parameter space of the training experimental data. For example, it is pointed out that all-dislocation-ceramics, which could be a new type of solid electrolyte filled with appropriate dislocations for high ionic conductivity without dendrite formation, could not be predicted by ML. The merits and demerits of first principles calculations and physical or phenomenological ODE model calculations are also discussed with some examples of the flexoelectric effect, dielectric constant, and ionic conductivity in solid electrolytes.Keywords
Funding Information
- Japan Science and Technology Agency (JST) (JPMJGX23SC)
This publication has 165 references indexed in Scilit:
- Distilling Free-Form Natural Laws from Experimental DataScience, 2009
- Nucleation and growth mechanism of ferroelectric domain-wall motionNature, 2007
- FEM calculation of an acoustic field in a sonochemical reactorUltrasonics Sonochemistry, 2007
- Theoretical study of single-bubble sonochemistryThe Journal of Chemical Physics, 2005
- Conducting nanowires in insulating ceramicsNature Materials, 2003
- Computational mineral physics and the physical properties of perovskitePhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2002
- The energy efficiency of formation of photons, radicals and ions during single-bubble cavitationNature, 2002
- Adiabatic density-functional perturbation theoryPhysical Review A, 1995
- Atoms, molecules, solids, and surfaces: Applications of the generalized gradient approximation for exchange and correlationPhysical Review B, 1992
- Green’s-function approach to linear response in solidsPhysical Review Letters, 1987