Analyzing machine learning models to accelerate generation of fundamental materials insights

Abstract

Machine learning for materials science envisions the acceleration of basic science research through automated identification of key data relationships to augment human interpretation and gain scientific understanding. A primary role of scientists is extraction of fundamental knowledge from data, and we demonstrate that this extraction can be accelerated using neural networks via analysis of the trained data model itself rather than its application as a prediction tool. Convolutional neural networks excel at modeling complex data relationships in multi-dimensional parameter spaces, such as that mapped by a combinatorial materials science experiment. Measuring a performance metric in a given materials space provides direct information about (locally) optimal materials but not the underlying materials science that gives rise to the variation in performance. By building a model that predicts performance (in this case photoelectrochemical power generation of a solar fuels photoanode) from materials parameters (in this case composition and Raman signal), subsequent analysis of gradients in the trained model reveals key data relationships that are not readily identified by human inspection or traditional statistical analyses. Human interpretation of these key relationships produces the desired fundamental understanding, demonstrating a framework in which machine learning accelerates data interpretation by leveraging the expertize of the human scientist. We also demonstrate the use of neural network gradient analysis to automate prediction of the directions in parameter space, such as the addition of specific alloying elements, that may increase performance by moving beyond the confines of existing data.npj Computational Materials (2019) 5:34 ; https://doi.

A brief review of data-driven ICME for intelligently discovering advanced structural metal materials: Insight into atomic and electronic building blocks

“…The flow chain of "Data-Cyber-Knowledge-Wisdom" presents the inheritable feature of the data in the frameworks of "Materials Genome," which is also highlighted in the Datadriven ICME designing paradigm of advanced materials. It is expected that the integration of knowledge-based multiscale modeling/simulations and the machine-learning self-knowledge base, materials design and discovery will be further accelerated [145,146]. More duties are called to contribute the developments of data repositories, platforms/standards, and the training of next-generation workforce.…”

Optimization of Material Composition of Li‐Intercalated Metal–Organic Framework Electrodes Using a Combination of Experiments and Machine Learning of X‐Ray Diffraction Patterns

“…Hence, to select an optimal material, we attempted to construct a machine learning-based prediction model using XRD patterns, instead of using the mixing ratios of raw material solutions. Although machine learning of patterns for MI has been reported previously, [23,24] a different method was required for our data, due to its complexity. As the XRD patterns were measured at a step size of 0.02° in the 5°-60° range, there are 2751 dimensions (data points) in a single pattern.…”

Progress and prospects for accelerating materials science with automated and autonomous workflows

“…The exploration of vast materials spaces (i.e. composition, structure, processing, morphology) via combinatorial materials science has yielded a wide variety of discoveries and advancements in fundamental knowledge 14,[18][19][20] and has additionally produced experiment databases with unprecedented breadth of materials and measured properties, as exemplied by the recent publication of the High Throughput Experimental Materials database (HTEM) 21 based on photovoltaics materials and the Materials Experiments and Analysis Database (MEAD) 22 based on solar fuels materials. These compilations of raw and analyzed 23 data from individual combinatorial materials science laboratories complement the suite of computational materials databases 60,61 as well as a rapidly growing number of materials data repositories including the Citrination platform, 24 the Materials Data Facility (MDF), 25 and text mining of the literature.…”