Methods, progresses, and opportunities of materials informatics

Abstract

As an implementation tool of data intensive scientific research methods, machine learning (ML) can effectively shorten the research and development (R&D) cycle of new materials by half or even more. ML shows great potential in the combination with other scientific research technologies, especially in the processing and classification of large amounts of material data from theoretical calculation and experimental characterization. It is very important to systematically understand the research ideas of material informatics to accelerate the exploration of new materials. Here, we provide a comprehensive introduction to the most commonly used ML modeling methods in material informatics with classic cases. Then, we review the latest progresses of prediction models, which focus on new processing–structure–properties–performance (PSPP) relationships in some popular material systems, such as perovskites, catalysts, alloys, two‐dimensional materials, and polymers. In addition, we summarize the recent pioneering researches in innovation of material research technology, such as inverse design, ML interatomic potentials, and microtopography characterization assistance, as new research directions of material informatics. Finally, we comprehensively provide the most significant challenges and outlooks related to the future innovation and development in the field of material informatics. This review provides a critical and concise appraisal for the applications of material informatics, and a systematic and coherent guidance for material scientists to choose modeling methods based on required materials and technologies.

Prediction of Photochromism of Salicylideneaniline Crystals Using a Data Mining Approach

“…First, we constructed a machine learning model to predict the crystal structural features, including dihedral angle, Hirshfeld surface volume, packing index, void volume per molecule, density, and C/C contact ratio, based on molecular structures. A gradient-boosted decision tree machine learning model implemented in XGBoost was employed for the model; XGBoost is used in various material science fields as it solves nonlinear regression problems, easily interprets the predicted output, and outperforms other algorithms in terms of prediction accuracy. − The molecular structures were represented as Morgan fingerprints for machine learning.…”

Solar‐Driven Hydrogen Evolution from Value‐Added Waste Treatment

“…As a result, ML can effectively shorten the period of searching and provide necessary assistance to the prediction of material properties, which avoids the time‐consuming trial‐and‐error laboratory experimental research. [ 241–245 ]…”

https://2DMat.ChemDX.org: Experimental data platform for 2D materials from synthesis to physical properties

“…In recent years, integrating data science and articial intelligence (AI) techniques into scientic research has triggered a transformative shi, particularly in materials exploration and optimization. [1][2][3][4][5][6][7][8][9][10][11] This shi has signicantly emphasized the values of "data" generated from experimental and computational processes, leading to the emergence of materials data platforms as indispensable tools in data-driven research. [12][13][14][15][16][17] These platforms facilitate convenient data collection, integration, utilization, and sharing.…”