A Survey of Artificial Intelligence Techniques Applied in Energy Storage Materials R&D

Abstract

Energy shortage is a severe challenge nowadays. It has affected the development of new energy sources. Artificial intelligence (AI), such as learning and analyzing, has been widely used for various advantages. It has been successfully applied to predict materials, especially energy storage materials. In this paper, we present a survey of the present status of AI in energy storage materials via capacitors and Li-ion batteries. We picture the comprehensive progress of AI in energy storage materials, including the advantages and disadvantages of material data to support AI. Finally, we provide some ideas to solve those challenges.

Artificial Intelligence Applied to Battery Research: Hype or Reality?

“…Informatics-aided materials discovery and optimization is becoming a powerful tool to analyze experimental and theoretical data and extract key structure–property relationships of functional materials, in general, and battery materials, in particular (recent review articles on the topic include refs , − ). Current approaches in this direction typically combine HT screening and ML, aiming to find new active electrode and electrolyte materials for next generation batteries.…”

Hybrid zinc‐air battery (ZAB) with transition metal‐based electrocatalysts—A step toward next‐generation electrochemical energy storage

“…This article gives a detailed and consolidated view on topics like introduction, the working mechanism of ZAB along with the advantages and disadvantages of using Transition metal‐based electrocatalysts in ZAB and the role of AI & ML in the development of the battery R&D field (Gao & Lu, 2021). Technologies, such as AI and ML are believed to be a great boon in the field of supercapacitor and battery‐related R&D studies which will be helpful to overcome challenges such as dealing with a large number of data and variables such as performance, analysis of life‐cycle, safety, cost, impact on the environment and obtaining raw materials (Luo et al, 2020; Mistry et al, 2021). Recently a lot of industries especially chemical industries started investing in combined AI and ML technologies to hasten R&D. And it has already been effectively used in the investigation of different fields such as materials, catalysts, pharmaceuticals and so forth (Schneider et al, 2020; Butler et al, 2018; Li et al, 2020; Tkatchenko, 2020; Venkatasubramanian, 2018).…”

Exploring the impact of dopants on ionic conductivity in solid‐state electrolytes: Unveiling insights using machine learning techniques

“…9 In this study, we employed optimized machine learning techniques, specifically random sampling screening of the Lazy classifier, to investigate the impact of different doping on the ionic conductivity of LLZO. 10,11 Furthermore, we examined the effect of various characteristics obtained from structural, molecular, and electronic descriptors on the quality of ionic conductivity. By investigating these factors, we aim to provide valuable guidance for the development of high-quality lithium-ion conductors.…”