Functional Output Regression for Machine Learning in Materials Science

16 May 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


In recent years, there has been a rapid growth in the use of machine learning in materials science. Conventionally, a trained predictive model describes a scalar output variable, such as thermodynamic, electronic, or mechanical properties, as a function of input descriptors that vectorize the compositional or structural features of any given material, such as molecules, chemical compositions, or crystalline systems. In machine learning of materials data, on the other hand, the output variable is often given as a function. For example, when predicting the optical absorption spectrum of a molecule, the output variable is a spectral function defined in the wavelength domain. Alternatively, in predicting the microstructure of a polymer nanocomposite, the output variable is given as an image from an electron microscope, which can be represented as a two- or three-dimensional function in the image coordinate system. In this study, we considered two unified frameworks to handle such multidimensional or functional output regressions, which are applicable to a wide range of predictive analyses in materials science. The first approach employs generative adversarial networks, which are known to exhibit outstanding performance in various computer vision tasks such as image generation, style transfer, and video generation. We also present another type of statistical modelling inspired by a statistical methodology referred to as functional data analysis. This is an extension of kernel regression to deal with functional outputs, and its simple mathematical structure makes it an effective modelling even for given data in limited supply. We demonstrate the proposed method through several case studies in materials science.


multidimensional output regressions
machine learning
functional output regressions
materials science

Supplementary materials

Supplementary Note Functional Output Regression for Machine Learning in Materials Science
Modelling details for cGAN and the functional output kernel regression, procedure of hyperparameter search, supplementary figures showing results of predicting the optical absorption spectra in the UV-Vis region and those in the USGS spectral library, and the microstructure image prediction.


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.