Abstract

New featurization schemes for describing materials as composition vectors in order to predict their properties using machine learning are common in the field of Materials Informatics. However, little is known about the comparative efficacy of these methods. This work sets out to make clear which featurization methods should be used across various circumstances. Our findings include, surprisingly, that simple fractional and random-noise representations of elements can be as effective as traditional and new descriptors when using large amounts of data. However, in the absence of large datasets or for data that is not fully representative, we show that the integration of domain knowledge offers advantages in predictive ability.

Graphical abstract

中文翻译：

---

机器学习材料属性是否需要领域知识？

摘要

在材料信息学领域中，用于将材料描述为成分向量以便使用机器学习预测其特性的新功能化方案很普遍。但是，对这些方法的比较功效知之甚少。着手这项工作是为了明确在各种情况下应使用哪种特征化方法。我们的发现令人惊讶地包括，当使用大量数据时，元素的简单分数和随机噪声表示可以与传统和新的描述符一样有效。但是，在没有大型数据集或没有完全代表的数据的情况下，我们表明领域知识的集成在预测能力上具有优势。

图形概要