Themed collection Editor’s Choice: Machine Learning for Materials Innovation

Zhen Zhou introduces a Journal of Materials Chemistry/Materials Advances Editor’s choice web collection on machine learning for materials innovation (https://rsc.li/MachineLearning).

Critical assessment of the present status of HEA NPs as catalysts, including an in-depth discussion of computational studies, combinatorial screening, or machine-learning studies to find the optimum composition and structure of HEA electrocatalysts.

Achieving the 2016 Paris agreement goal of limiting global warming below 2 °C and securing a sustainable energy future require materials innovations in renewable energy technologies. Machine learning has demonstrated many successes to accelerate the discovery renewable energy materials.

We demonstrate, for the first time, a transient, flexible multifunctional sensor (strain, pressure, and breath) using a water soluble SnS₂-QD/PVA film.

We built machine learning-based models to predict the performance of filtration membranes, and integrated them into homemade standalone software (polySML).

With maximum atom-utilization efficiency, single atom catalysts (SACs) are surging as a new research frontier in catalysis science.

Based on the understandings of alloying effects in bimetallic (100) surfaces, we explored their four-fold active sites for electrocatalytic hydrogen evolution reaction.

Gapped metals present in their band structure a gap near the Fermi level. This key feature makes these metals comparable to degenerate semiconductors and thus suitable as thermoelectrics. The present screening searches them systematically.

We develop a universal design scheme based on the machine learning method and the intrinsic properties of substrates and adsorbates, allowing accurate prediction and rapid screening through a large phase space of alloys and multiple adsorbates.

Pilot plant optimization of CO₂RR system to produce CO via Ag electrodes have been performed and the results are intensely studied via correlation analysis.

This work evaluates the application of machine learning in the construction automation.

Fast material search using a recommender system is demonstrated to obtain novel lithium ion conducting oxides.

Electronic and thermal transport in materials originate from various forms of electron and ion interactions.

The oxygen reduction reaction (ORR), oxygen evolution reaction (OER), and hydrogen evolution reaction (HER) are three critical reactions for energy-related applications, such as water electrolyzers and metal–air batteries.

Machine learning (ML) methods would significantly reduce the computational burden of catalysts screening for nitrogen reduction reaction (NRR).

By a two-step computational process, namely Grand Canonical Monte Carlo (GCMC) simulations and machine learning (ML), we screened 50 959 hypothetical pure-silica zeolites and identified 230 preeminent zeolites with excellent adsorption performances.

The advent of machine learning (ML) techniques in solving problems related to materials science and chemical engineering is driving expectations to give faster predictions of material properties.

High-throughput computational screening of millions of cascaded adsorption heat pumps based on metal–organic frameworks and covalent–organic frameworks.

Lithium metal batteries are a promising candidate for future high-energy-density energy storage.

The intercalation of alkali metals in disordered carbon anode materials is studied by a combination of first-principles and machine-learning methods.

Rational design of new OPV molecules via virtual screening of candidate materials using high-performing machine learning models.

Developing novel hydrocarbon-based proton exchange membranes is at the Frontier of research on fuel cells, batteries and electrolysis, aiming to reach the demand for advanced performance in proton conductivity, fuel retardation, swelling, mechanical and thermal stability etc.

This paper reports side-chain-engineered polymer donors and a small-molecule acceptor that are capable of simultaneous charge and energy transfer as the active layer for organic photovoltaics.

Crystalline nanoporous materials (i.e. shapes) were generated in the energy space using an artificial neural network.