These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
3 files

Accurate Multi-Objective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization

submitted on 13.12.2019, 20:39 and posted on 20.12.2019, 06:28 by Jon Paul Janet, Sahasrajit Ramesh, Chenru Duan, Heather Kulik

The accelerated discovery of materials for real world applications requires the achievement of multiple design objectives. Satisfaction of such constraints requires exploration of multi-million compound libraries over which even density-functional theory (DFT) screening is intractable. Machine learning (ML, e.g., artificial neural network, ANN, or Gaussian process, GP) models for this task are limited by training data availability and predictive uncertainty quantification (UQ). We overcome such limitations by using efficient global optimization (EGO) with the multi-dimensional expected improvement (EI) criterion. EGO balances exploitation of a trained model with acquisition of new DFT data at the Pareto front, the region of chemical space that contains the optimal trade-off between multiple design criteria. We demonstrate this approach for the simultaneous optimization of redox potential and solubility in candidate M(II)/M(III) redox couples for redox flow batteries from a space of 2.8M transition metal complexes designed for stability in practical RFB applications. We employ latent-distance-based UQ with a multi-task ANN to enable model generalization that surpasses that of a GP. With this approach, ANN prediction and EI scoring of the full 2.8M complex space is achieved in minutes. Starting from ca. 100 representative points, EGO improves both properties by 3-4 standard deviations in only five generations. Analysis of lookahead errors confirms rapid ANN model improvement during the EGO process, achieving suitable accuracy for predictive design in the space of transition metal complexes. The ANN-driven EI approach achieves at least 500-fold acceleration over random search, identifying a Pareto-optimal design in around five weeks instead of fifty years.


Office of Naval Research N00014-18-1-2434

DARPA Grant D18AP00039

Simultaneous mitigation of density and energy errors in approximate DFT for transition metal chemistry

Basic Energy Sciences

Find out more...

AAAS Marion Milligan Mason Award


Email Address of Submitting Author


Massachusetts Institute of Technology



ORCID For Submitting Author


Declaration of Conflict of Interest

The authors declare no conflict of interest