Electrolyte discovery is the bottleneck for developing next generation batteries. For example, lithium metal batteries (LMBs) promise to double the energy density of current Li-ion batteries (LIBs) while next generation LIBs are desired for operations at extreme temperature conditions and with high voltage cathodes. However, there are no suitable electrolytes to support these battery chemistries. Electrolyte requirements are complex (conductivity, stability, safety) and the chemical design space (salts, solvents, additives, composition) is practically infinite; hence discovery is primarily guided through trial-and-error which slows the deployment of new battery chemistries. Inspired by artificial intelligence (AI)-enabled drug discovery, we usher in a new paradigm for electrolyte discovery. We assemble the largest small molecule experimental liquid electrolyte ionic conductivity dataset and build highly accurate machine learning (ML) and deep learning models to predict ionic conductivity across a wide range of electrolyte classes. The developed models outperform molecular dynamic (MD) simulations and are interpretable without explicit encoding of ionic solvation. While most ML-based approaches target a single property, we build additional models of oxidative stability and Coulombic efficiency and develop a new metric called the electrolyte score (eScore) to unify the predicted disparate electrolyte properties. Deploying these models on large unlabeled datasets, we discover new electrolyte solvents, experimentally validate that the electrolyte is conductive (> 1 mS cm-1), stable up to 6V, supports efficient anode-free LMB, and even LIB cycling at extreme temperatures. Our work heralds a new age in electrolyte design and battery materials discovery.

中文翻译：

---

电解组学：用于电解质设计和发现的统一大数据方法

电解质的发现是开发下一代电池的瓶颈。例如，锂金属电池 (LMB) 有望将当前锂离子电池 (LIB) 的能量密度提高一倍，而下一代 LIB 则需要在极端温度条件下运行并采用高压阴极。然而，没有合适的电解质来支持这些电池化学成分。电解质要求很复杂（导电性、稳定性、安全性），化学设计空间（盐、溶剂、添加剂、成分）实际上是无限的；因此，发现主要是通过反复试验来引导的，这会减慢新电池化学物质的部署。受人工智能 (AI) 支持的药物发现的启发，我们开创了电解质发现的新范例。我们组装了最大的小分子实验液体电解质离子电导率数据集，并构建了高度准确的机器学习 (ML) 和深度学习模型，以预测各种电解质类别的离子电导率。开发的模型优于分子动力学（MD）模拟，并且无需离子溶剂化的显式编码即可解释。虽然大多数基于机器学习的方法都针对单一属性，但我们构建了氧化稳定性和库仑效率的附加模型，并开发了一种称为电解质评分 (eScore) 的新指标，以统一预测的不同电解质属性。在大型未标记数据集上部署这些模型，我们发现了新的电解质溶剂，通过实验验证了电解质的导电性（> 1 mS cm-1）、在高达 6V 的电压下稳定、支持高效的无阳极 LMB，甚至在极端温度下的 LIB 循环。我们的工作预示着电解质设计和电池材料发现的新时代。