Discovery of Energy Storage Materials Using Multi-objective Bayesian Optimization

(a) Multi-objective design parameters of anolytes for redox flow batteries. (b) Identification of Pareto-optimal molecules from the DFT-simulated dataset. (c) Performance evaluation of molecular optimization in comparison to random selection.

Scientific Achievement

Designing optimal materials for redox flow batteries is challenging due to the multi-criteria requirement and large number of potential candidates. Multi-objective Bayesian optimization (MBO) was developed and demonstrated to significantly accelerate (15-fold) the identification of anolyte molecules of desired reduction potential, solubility, and fluorescence from a large chemical space.

Significance and Impact

Our MBO approach shows a 15-fold improvement in efficiency over random selection and identified 16 new anolytes  after evaluating only 100 out of 1 million candidates.

Research Details

  • Density functional theory (DFT) was carried out on chemist-proposed 1400 data set of 2,1,3-benzothiadiazole (BzNSN) derivatives to compute the reduction potentials (Ered), solvation free energies (Gsolv), and absorption wavelengths (λabs) .
  • MBO was first developed, tuned, and benchmarked on the DFT-computed data set, and then employed on new molecular dataset of 1 million BzNSN molecules to identify anolytes with desired design parameters.

Download this highlight

DOI: 10.1021/acs.chemmater.1c02040


Latest Updates

See All