Evaluating uncertainty-based active learning for accelerating the generalization of molecular property prediction.

Deep learning models have proven to be a powerful tool for the prediction of molecular properties for applications including drug design and the development of energy storage materials. However, in order to learn accurate and robust structure-property mappings, these models require large amounts of data which can be a challenge to collect given the time and resource-intensive nature of experimental material characterization efforts. Additionally, such models fail to generalize to new types of molecular structures that were not included in the model training data.

SOMAS: a platform for data-driven material discovery in redox flow battery development.

Aqueous organic redox flow batteries offer an environmentally benign, tunable, and safe route to large-scale energy storage. The energy density is one of the key performance parameters of organic redox flow batteries, which critically depends on the solubility of the redox-active molecule in water. Prediction of aqueous solubility remains a challenge in chemistry.

Evaluation of Deep Learning Architectures for Aqueous Solubility Prediction.

Determining the aqueous solubility of molecules is a vital step in many pharmaceutical, environmental, and energy storage applications. Despite efforts made over decades, there are still challenges associated with developing a solubility prediction model with satisfactory accuracy for many of these applications. The goals of this study are to assess current deep learning methods for solubility prediction, develop a general model capable of predicting the solubility of a broad range of organic molecules, and to understand the impact of data properties, molecular representation, and modeling architecture on predictive performance.

Machine-Learning Prediction of CO Adsorption in Thiolated, Ag-Alloyed Au Nanoclusters.

We propose a machine-learning model, based on the random-forest method, to predict CO adsorption in thiolate protected nanoclusters. Two phases of feature selection and training, based initially on the Au nanocluster, are utilized in our model. One advantage to a machine-learning approach is that correlations in defined features disentangle relationships among the various structural parameters.

Structural and catalytic properties of the AuAg(SCH) (x = 6, 7, 8) nanocluster.

In this study, we explore the structural, electronic and catalytic properties of bimetallic nanoparticles of the form Au25-xAgx(SR)18 (for x = 6, 7, 8). Due to the combinatorial enormity of the number of different alloyed structures, we choose 500 random configurations corresponding to each alloying level and energetically optimize their structures. Here we report the properties of the lowest energy structures and determine the most favorable Ag alloying sites for these systems.

Controlling Ag-doping in [AgAu(SCH)] nanoclusters: cryogenic optical, electronic and electrocatalytic properties.

Doping metal nanoclusters with a second type of metal is a powerful method for tuning the physicochemical properties of nanoclusters at the atomic level and it also provides opportunities for a fundamental understanding of alloying rules as well as new applications. Herein, we have devised a new, one-phase strategy for achieving heavy Ag-doping in Au(SR) nanoclusters. This strategy overcomes the light doping of silver by previous methods.

Slow Relaxation of Surface Plasmon Excitations in Au55: The Key to Efficient Plasmonic Heating in Au/TiO2.

Gold nanoparticles distinguish themselves from other nanoparticles due to their unique surface plasmon resonance properties that can be exploited for a multiplicity of applications. The promise of plasmonic heating in systems of Au nanoparticles on transition metal oxide supports, for example, Au/TiO2, rests with the ability of the surface plasmon in Au nanoparticles to effectively transfer energy into the transition metal oxide. Here, we report a critical observation regarding Au nanoparticle (Au55) surface plasmon excitations, that is, the relaxation of the surface plasmon excitation is very slow, on the order of several picoseconds.