Accurate Multiobjective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization
Accurate Multiobjective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization
复制标题
DOI：
10.1021/acscentsci.0c00026
复制
发表时间：
2020-04-22
影响因子：
18.2
通讯作者：
Kulik, Heather J.
中科院分区：
文献类型：
--
作者：
Janet, Jon Paul;Ramesh, Sahasrajit;Kulik, Heather J.
加速发现用于真实的世界应用的材料需要实现多个设计目标。搜索的多维性需要探索数百万的化合物库，即使是密度泛函理论（DFT）筛选也是棘手的。机器学习（例如，人工神经网络ANN或高斯过程GP）模型受到训练数据可用性和预测不确定性量化（UQ）的限制。我们克服了这些限制，使用有效的全局优化（EGO）与多维预期改善（EI）标准。EGO平衡了训练模型的利用与帕累托前沿新DFT数据的获取，帕累托前沿是包含多个设计标准之间的最佳权衡的化学空间区域。我们证明了这种方法的氧化还原电位和溶解度的同时优化的候选人M（II）/M（III）氧化还原对氧化还原液流电池从空间的2.8 M过渡金属络合物设计的稳定性，在实际的氧化还原液流电池（RFB）的应用。我们表明，一个多任务人工神经网络与潜在的距离为基础的UQ超越在这个空间中的GP的泛化性能。利用这种方法，在几分钟内实现了全空间的ANN预测和EI评分。从CA开始。100个代表点，EGO在五代内将这两个属性提高了3个标准差。前瞻性错误的分析证实了快速的神经网络模型的改进过程中的EGO，实现适当的准确性，在过渡金属配合物的空间预测设计。人工神经网络驱动的EI方法比随机搜索实现了至少500倍的加速，在大约5周而不是50年内确定了帕累托最优设计。
The accelerated discovery of materials for real world applications requires the achievement of multiple design objectives. The multidimensional nature of the search necessitates exploration of multimillion compound libraries over which even density functional theory (DFT) screening is intractable. Machine learning (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 multidimensional 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 2.8 M transition metal complexes designed for stability in practical redox flow battery (RFB) applications. We show that a multitask ANN with latent-distance-based UQ surpasses the generalization performance of a GP in this space. With this approach, ANN prediction and EI scoring of the full space are achieved in minutes. Starting from ca. 100 representative points, EGO improves both properties by over 3 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 5 weeks instead of 50 years.