Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Achieving autonomous multi-step synthesis of novel molecular structures in chemical discovery processes is a goal shared by many researchers. In this Comment, we discuss key considerations of what an ideal platform may look like and the apparent state of the art. While most hardware challenges can be overcome with clever engineering, other challenges will require advances in both algorithms and data curation.
Useful materials must satisfy multiple objectives. The Pareto front expresses the trade-offs of competing objectives. This work uses a self-driving laboratory to map out the Pareto front for making highly conductive coatings at low temperatures.
Electrons and phonons give rise to important properties of materials. The machine learning framework Mat2Spec vastly accelerates their computational characterization, enabling discovery of materials for thermoelectrics and solar energy technologies.
The present manuscript reports a Bayesian deep-learning approach for the automatic, robust classification of polycrystalline systems of both synthetic and experimental origin. The unsupervised analysis of the internal neural-network representations reveals physically understandable patterns.
Machine learning has the potential to significantly speed-up the discovery of new materials in synthetic materials chemistry. Here the authors combine unsupervised machine learning and crystal structure prediction to predict a novel quaternary lithium solid electrolyte that is then synthesized.
Understanding the catalysts’ structure evolution under working conditions is challenging. Here the authors use a multiscale simulation approach and machine learning to study the structures and nucleation of CeO2-supported Pd clusters and single atoms at various catalyst loadings, temperatures, and exposures to CO.
Predictive computational approaches are fundamental to accelerating solid-state inorganic synthesis. This work demonstrates a computational tractable approach constructed from available thermochemistry data and based on a graph-based network model for predicting solid-state inorganic reaction pathways.
Identifying optimal materials in multiobjective optimization problems represents a challenge for new materials design approaches. Here the authors develop an active-learning algorithm to optimize the Pareto-optimal solutions successfully applied to the in silico polymer design for a dispersant-based application.
Energy–structure–function (ESF) maps can facilitate functional materials discovery. Here the authors provide a protocol for the digital navigation of ESF maps, as demonstrated for hydrogen-bonded organic frameworks constructed from triptycene- and spiro-biphenyl-based molecular building block.
Predicting the structure of unknown materials’ compositions represents a challenge for high-throughput computational approaches. Here the authors introduce a new stoichiometry-based machine learning approach for predicting the properties of inorganic materials from their elemental compositions.
Machine learning driven research holds big promise towards accelerating materials’ discovery. Here the authors demonstrate CAMEO, which integrates active learning Bayesian optimization with practical experiments execution, for the discovery of new phase- change materials using X-ray diffraction experiments.
Over the last decade, we have witnessed the emergence of ever more machine learning applications in all aspects of the chemical sciences. Here, we highlight specific achievements of machine learning models in the field of computational chemistry by considering selected studies of electronic structure, interatomic potentials, and chemical compound space in chronological order.
Discovering chemicals with desired attributes is a long and painstaking process. Curated datasets containing reliable quantum-mechanical properties for millions of molecules are becoming increasingly available. The development of novel machine learning tools to obtain chemical knowledge from these datasets has the potential to revolutionize the process of chemical discovery. Here, I comment on recent breakthroughs in this emerging field and discuss the challenges for the years to come.
Photon-induced charge separation phenomena are at the heart of light-harvesting applications but challenging to be described by quantum mechanical models. Here the authors illustrate the potential of machine-learning approaches towards understanding the fundamental processes governing electronic excitations.
The stability of perovskite solar cells can be improved by using hybrid-organic perovskites capping-layers atop the active material. Here the authors use machine learning to optimize capping layers by monitoring time to degradation of differently capped lead-halide perovskite solar cells.
Symbolic regression holds big promise for guiding materials design, yet its application in materials science is still limited. Here the authors use symbolic regression to introduce an activity descriptor predicting new oxide perovskites with improved oxygen evolution activity as corroborated by experimental validation.
Crystallization is a challenging process to model quantitatively. Here the authors use machine learning and atomistic simulations together to uncover the role of the liquid structure on the process of crystallization and derive a predictive kinetic model of crystal growth.
Knowing compositional motifs of nanoparticle catalysts in operando conditions is crucial towards understanding their catalytic behavior. Here, the authors develop a physics-driven machine learning approach to predict adsorption sites for a CO molecule over platinum nanoparticles in a multitude of coordination environments.
Machine-learning approaches based on DFT computations can greatly enhance materials discovery. Here the authors leverage existing large DFT-computational data sets and experimental observations by deep transfer learning to predict the formation energy of materials from their elemental compositions with high accuracy.
Predictions of new solid-state Li-ion conductors are challenging due to the diverse chemistries and compositions involved. Here the authors combine unsupervised learning techniques and molecular dynamics simulations to discover new compounds with high Li-ion conductivity.
Predicting the synthesizability of inorganic materials is challenging due to the many variables and complex phenomena involved in synthesis. Here, the authors combine material stabilities with a historical analysis of experimental discovery timelines as a temporal network to predict the synthesizability of hypothetical materials.
While the conversion of greenhouse CO2 to chemical fuels offers a promising renewable energy technology, there is a dire need for new materials. Here, authors report the largest CO2 photocathode search using a first-principles approach to identify both known and unreported candidate photocatalysts.
Solid-state nuclear magnetic resonance combined with quantum chemical shift predictions is limited by high computational cost. Here, the authors use machine learning based on local atomic environments to predict experimental chemical shifts in molecular solids with accuracy similar to density functional theory.
Crystal stability prediction is of paramount importance for novel material discovery, with theoretical approaches alternative to expensive standard schemes highly desired. Here the authors develop a deep learning approach which, just using two descriptors, provides crystalline formation energies with very high accuracy.