Recent advances in machine learning technologies and their applications have led to the development of diverse structure–property relationship models for crucial chemical properties. The solvation free energy is one of them. Here, we introduce a novel ML-based solvation model, which calculates the solvation energy from pairwise atomistic interactions. The novelty of the proposed model consists of a simple architecture: two encoding functions extract atomic feature vectors from the given chemical structure, while the inner product between the two atomistic feature vectors calculates their interactions. The results of 6239 experimental measurements achieve outstanding performance and transferability for enlarging training data owing to its solvent-non-specific nature. An analysis of the interaction map shows that our model has significant potential for producing group contributions on the solvation energy, which indicates that the model provides not only predictions of target properties but also more detailed physicochemical insights.
Redox-active organic materials (ROMs) hold great promise as potential electrode materials for eco-friendly, costeffective, and sustainable batteries; however, the poor cycle stability arising from the chronic dissolution issue of the ROMs in generic battery systems has impeded their practical employment. Herein, we present that a rational selection of electrolytes considering the solubility tendency can unlock the hidden full redox capability of the DMPZ electrode (i.e., 5,10-dihydro-5,10dimethylphenazine) with unprecedentedly high reversibility. It is demonstrated that a multiredox activity of DMPZ/DMPZ + / DMPZ 2+ , which has been previously regarded to degrade with repeated cycles, in the newly designed electrolyte can be utilized with surprisingly robust cycle stability over 1000 cycles at 1C. This work signifies that tailoring the electrode−electrolyte compatibility can possibly unleash the hidden potential of many common ROMs, catalyzing the rediscovery of organic electrodes with long-lasting and high energy density.
Recent advances in machine learning technologies and their applications have led to the development of diverse structure-property relationship models for crucial chemical properties. The solvation free energy is one of them. Here, we introduce a novel ML-based solvation model, which calculates the solvation energy from pairwise atomistic interactions. The novelty of the proposed model consists of a simple architecture: two encoding functions extract atomic feature vectors from the given chemical structure, while the inner product between the two atomistic features calculates their interactions. The results of 6,493 experimental measurements achieve outstanding performance and transferability for enlarging training data owing to its solvent-non-specific nature. An analysis of the interaction map shows that our model has significant potential for producing group contributions on the solvation energy, which indicates that the model provides provides not only predictions of target properties but also more detailed physicochemical insights.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.