遗传算法是受达尔文进化论启发的优化算法，是新材料发掘的重要工具。遗传算法的精度依赖于材料的势能面描述的准确性。而采用精确的密度泛函能量计算的遗传算法，计算量巨大，限制了其在新材料发掘方面的应用。

来自丹麦技术大学和斯坦福大学的Tejs Vegge团队采用机器学习模型作为快速的能量预测工具，将机器学习与遗传算法耦合，在加速搜索方面表现出显著的优势。以纳米合金催化剂为例，他们采用该方法搜索采用其搜索了稳定的、组分变化的、几何相似的铂-金二元纳米合金颗粒。在该算例中，机器学习加速方法相比传统的“暴力”遗传算法所需对能量计算的数量减少了50倍。该方法使得基于精确密度泛函能量计算的遗传算法应用于新材料发掘成为可能。

该文近期发表于npj Computational Materials 5: 46 (2019)，英文标题与摘要如下，点击可以自由获取论文PDF。

Genetic algorithms for computational materials discovery accelerated by machine

Paul C. Jennings, Steen Lysgaard, Jens Strabo Hummelshøj, Tejs Vegge & Thomas Bligaard

Materials discovery is increasingly being impelled by machine learning methods that rely on pre-existing datasets. Where datasets are lacking, unbiased data generation can be achieved with genetic algorithms. Here a machine learning model is trained on-the-fly as a computationally inexpensive energy predictor before analyzing how to augment convergence in genetic algorithm-based approaches by using the model as a surrogate. This leads to a machine learning accelerated genetic algorithm combining robust qualities of the genetic algorithm with rapid machine learning. The approach is used to search for stable, compositionally variant, geometrically similar nanoparticle alloys to illustrate its capability for accelerated materials discovery, e.g., nanoalloy catalysts. The machine learning accelerated approach, in this case, yields a 50-fold reduction in the number of required energy calculations compared to a traditional “brute force” genetic algorithm. This makes searching through the space of all homotops and compositions of a binary alloy particle in a given structure feasible, using density functional theory calculations.