Machine Learning Boosting the Development of Advanced Lithium Batteries

Toward High-Performance Li-Rich Mn-Based Layered Cathodes: A Review on Surface Modifications

Lithium-rich manganese-based layered oxides (LRMOs) have received attention from both the academic and the industrial communities in recent years due to their high specific capacity (theoretical capacity ≥250 mAh g-1), low cost, and excellent processability. However, the large-scale applications of these materials still face unstable surface/interface structures, unsatisfactory cycling/rate performance, severe voltage decay, etc. Recently, solid evidence has shown that lattice oxygen in LRMOs easily moves and escapes from the particle surface, which inspires significant efforts on stabilizing the surface/interfacial structures of LRMOs. In this review, the main issues associated with the surface of LRMOs together with the recent advances in surface modifications are outlined. The critical role of outside-in surface decoration at both atomic and mesoscopic scales with an emphasis on surface coating, surface doping, surface structural reconstructions, and multiple-strategy co-modifications is discussed. Finally, the future development and commercialization of LRMOs are prospected. Looking forward, the optimal surface modifications of LRMOs may lead to a low-cost and sustainable next-generation high-performance battery technology.

Solutions for Lithium Battery Materials Data Issues in Machine Learning: Overview and Future Outlook

The application of machine learning (ML) techniques in the lithium battery field is relatively new and holds great potential for discovering new materials, optimizing electrochemical processes, and predicting battery life. However, the accuracy of ML predictions is strongly dependent on the underlying data, while the data of lithium battery materials faces many challenges, such as the multi-sources, heterogeneity, high-dimensionality, and small-sample size. Through the systematic review of the existing literatures, several effective strategies are proposed for data processing as follows: classification and extraction, screening and exploration, dimensionality reduction and generation, modeling and evaluation, and incorporation of domain knowledge, with the aim to enhance the data quality, model reliability, and interpretability. Furthermore, other possible strategies for addressing data quality such as database management techniques and data analysis methodologies are also emphasized. At last, an outlook of ML development for data processing methods is presented. These methodologies are not only applicable to the data of lithium battery materials, but also endow important reference significance to electrocatalysis, electrochemical corrosion, high-entropy alloys, and other fields with similar data challenges.

Data-Driven Battery Characterization and Prognosis: Recent Progress, Challenges, and Prospects

Battery characterization and prognosis are essential for analyzing underlying electrochemical mechanisms and ensuring safe operation, especially with the assistance of superior data-driven artificial intelligence systems. This review provides a unique perspective on recent progress in data-driven battery characterization and prognosis methods. First, recent informative image characterization and impedance spectrum as well as high-throughput screening approaches on revealing battery electrochemical mechanisms at multiple scales are summarized. Thereafter, battery prognosis tasks and strategies are described, with the comparison of various physics-informed modeling strategies. Considering unlocking mechanisms from tremendous battery data, the dominant role of physics-informed interpretable learning in accelerating energy device development is presented. Finally, challenges and prospects on data-driven characterization and prognosis are discussed toward accelerating energy device development with much-enhanced electrochemical transparency and generalization. This review is hoped to supply new ideas and inspirations to the next-generation battery development.

Building Smarter Aqueous Batteries

Amidst the global trend of advancing renewable energies toward carbon neutrality, energy storage becomes increasingly critical due to the intermittency of renewables. As an alternative to lithium-ion batteries (LIBs), aqueous batteries have received growing attention for large-scale energy storage due to their economical and safe features. Despite the fruitful achievements at the material level, the reliability and lifetime of aqueous batteries are still far from satisfactory. Alike LIBs, integrating smartness is essential for more reliable and long-life aqueous batteries via operando monitoring and automatic response to extreme abuses. In this review, recent advances in sensing techniques and multifunctional battery-sensor systems together with self-healing methods in aqueous batteries is summarized. The significant role of artificial intelligence in designing and optimizing aqueous batteries with high efficiency is also highlighted. Ultimately, it is extrapolated toward the future and present the humble perspective for building smarter aqueous batteries.

Construction of greenly biodegradable bacterial cellulose/UiO-66-NH2 composite separators for efficient enhancing performance of lithium-ion battery

The disposal of waste lithium batteries, especially waste separators, has always been a problem, incineration and burial will cause environmental pollution, therefore, the development of degradable and high-performance separators has become an important challenge. Herein, UiO-66-NH2 particles were successfully anchored onto bacterial cellulose (BC) separators by epichlorohydrin (ECH) as a crosslinker, then a BC/UiO-66-NH2 composite separator was prepared by vacuum filtration. The ammonia groups (-NH2) from UiO-66-NH2 can form hydrogen bonds with PF6- in the electrolyte, promoting lithium-ion transference. Additionally, UiO-66-NH2 can store the electrolyte and tune the porosity of the separator. The lithium ion migration number (0.62) of the battery assembled with BC/UiO-66-NH2 composite separator increased by 50 % compared to the battery assembled with commercial PP separator (0.45). The discharge specific capacity of the battery assembled with BC/UIO-66-NH2 composite separator after 50 charge and discharge cycles is 145.4 mAh/g, which is higher than the average discharge specific capacity of 114.3 mAh/g of the battery assembled with PP separator. When the current density is 2C, the minimum discharge capacity of the battery assembled with BC/UiO-66-NH2 composite separator is 85.3 mAh/g. The electrochemical performance of the BC/UiO-66-NH2 composite separator is significantly better than that of the commercial PP separator. In addition, -NH2 can offer a nitrogen source to facilitate degradation of the BC separators, whereby the BC/UiO-66-NH2 composite separator could be completely degraded in 15 days.

A Critical Review of Machine Learning Techniques on Thermoelectric Materials

Thermoelectric (TE) materials can directly convert heat to electricity and vice versa and have broad application potential for solid-state power generation and refrigeration. Over the past few decades, efforts have been made to develop new TE materials with high performance. However, traditional experiments and simulations are expensive and time-consuming, limiting the development of new materials. Machine learning (ML) has been increasingly applied to study TE materials in recent years. This paper reviews the recent progress in ML-based TE material research. The application of ML in predicting and optimizing the properties of TE materials, including electrical and thermal transport properties and optimization of functional materials with targeted TE properties, is reviewed. Finally, future research directions are discussed.

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid and solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high ionic conductivity SPEs, we developed a chemistry-informed machine learning model that accurately predicts ionic conductivity of SPEs. The model was trained on SPE ionic conductivity data from hundreds of experimental publications. Our chemistry-informed model encodes the Arrhenius equation, which describes temperature activated processes, into the readout layer of a state-of-the-art message passing neural network and has significantly improved accuracy over models that do not encode temperature dependence. Chemically informed readout layers are compatible with deep learning for other property prediction tasks and are especially useful where limited training data are available. Using the trained model, ionic conductivity values were predicted for several thousand candidate SPE formulations, allowing us to identify promising candidate SPEs. We also generated predictions for several different anions in poly(ethylene oxide) and poly(trimethylene carbonate), demonstrating the utility of our model in identifying descriptors for SPE ionic conductivity.

First-principles materials simulation and design for alkali and alkaline metal ion batteries accelerated by machine learning

The challenge of regeneration of batteries requires a performance improvement in the alkali/alkaline metal ion battery (AMIB) materials, whereas the traditional research paradigm fully based on experiments and theoretical simulations needs massive research and development investment. During the last decade, machine learning (ML) has made breakthroughs in many complex disciplines, which testifies to their high processing speed and ability to capture relationships. Inspired by these achievements, ML has also been introduced to bring a new paradigm for shortening the development of AMIB materials. In this Perspective, the focus will be on how this new ML technology solves the key problems of redox potentials, ionic conductivity and stability parameters in first-principles materials' simulation and design for AMIBs. It is found that ML not only accelerates the property prediction, but also gives physicochemical insights into AMIB materials' design. In addition, the final part of this paper summarizes current achievements and looks forward to the progress of a novel paradigm in direct/inverse design with the increasing number of databases, skills, and ML technologies for AMIBs.