Interpretable learning of voltage for electrode design of multivalent metal-ion batteries

A CGCNN model is developed for learning electrode voltages of multivalent MIBs at small datasets (150–500). The model is much more accurate than traditional ML models with an MAE of around 0.5 V. The DL model is also explainable and extracts the atom covalent radius as the most important feature.
Published in Materials
Interpretable learning of voltage for electrode design of multivalent metal-ion batteries

Share this post

Choose a social network to share with, or copy the shortened URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Lithium-ion batteries (LIBs) have shown great success as the major power source for transportation and as an energy storage solution for grid applications. Nowadays, the relatively low-energy density and the scarcity of Li raw materials are the main issues of LIBs for large-scale applications. These issues call for high density, cheaper and sustainable alternatives to present LIB technologies. Multivalent metal-ion batteries (MIBs), including Mg2+, Ca2+, Zn2+, Al3+, have the potential to meet this purpose, due to the relatively high abundance of these elements in the Earth’s crust and high-energy density. But the study of these MIBs' properties is time and computational and experimental resource consuming. Luckily, within the arena of big data, deep learning (DL) has emerged as a game-changing technique very recently, enabling numerous scientific applications in chemistry, mathematics, physics, and biology. The high-performance  DL model is of high need for predicting a variety of properties of multivalent MIBs and then designing high-performing multivalent MIBs.

Recently, Prof. Shen from Department of Mechanical Engineering, National University of Singapore cooperating with Prof. Lv from State Key Laboratory of Mesoscopic Physics and Department of Physics, Peking University have trained a DL model to correctly predict the voltages of the muti-valent MIBs. They take the voltage of multivalent MIBs as an example to demonstrate how an interpretable deep transfer-learning (TL) model, can be used for exploration and design of electrode materials for battery applications, addressing the conventional ML issues (low prediction accuracy and heavy feature-engineering dependence) and DL limitations (low interpretability and high big-data demand). It is worth noting that high-voltage electrode materials can enhance the voltage platform of batteries, which is the key component for high-energy density MIBs and is generally used in the performance prediction of materials of battery electrodes. They firstly train the DL models with relatively large data of the electrode voltage of LIBs (2000+ data) from Materials Project (MP). It is found that MAE of LIBs is only 0.32 V. Nevertheless, MAE of multivalent MIBs is significantly high (up to 2.14 V) using the same method because of small datasets of multivalent MIBs (as low as 149). They, thus, integrate the TL technique, widely used to address less data restriction, into the DL models. It greatly reduces the MAEs for Zn-, Ca-, Mg-, and Al-ion batteries, for example, from 2.14 V down to only 0.47 V for the Zn-ion battery. To interpret the DL models, they perform the visualization of the similarity between the elements and local environments in different layers of the deep-neural network. The DL models can automatically hierarchically extract key features and explain the different contributions of element groups in the periodic table to the corresponding electrode voltages. Their results show that the highly accurate and interpretable deep model could accelerate the discovery and design of electrode materials for multivalent MIBs and the development of the large-scale battery industry. A publicly available online tool kit is built in for the battery community.

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in

Subscribe to the Topic

Materials Science
Physical Sciences > Materials Science

Related Collections

With collections, you can get published faster and increase your visibility.

Transport Mechanisms in Energy Materials

The integration of computational material methods, artificial intelligence technology, and advanced in-situ experimental characterization techniques constitutes a foundational approach for unraveling the microstructural transport mechanisms within energy materials. The recent surge in mechanism elucidation, powered by these integrated methodologies, is widely acknowledged as a pivotal avenue for material innovations, consequently propelling advancements in new energy applications. This collection is dedicated to tracking the latest developments and publishing intriguing investigations pertaining to transport mechanisms within energy materials.

Publishing Model: Open Access

Deadline: Oct 31, 2024

Computational Progress of High Entropy Materials

We invite submissions of papers focusing on the computational progress of high entropy materials.

Publishing Model: Open Access

Deadline: Jul 07, 2024