Machine Learning Coupled Multi‐Scale Modeling for Redox Flow Batteries

Machine learning for flow batteries: opportunities and challenges

With increased computational ability of modern computers, the rapid development of mathematical algorithms and the continuous establishment of material databases, artificial intelligence (AI) has shown tremendous potential in chemistry. Machine learning (ML), as one of the most important branches of AI, plays an important role in accelerating the discovery and design of key materials for flow batteries (FBs), and the optimization of FB systems. In this perspective, we first provide a fundamental understanding of the workflow of ML in FBs. Moreover, recent progress on applications of the state-of-art ML in both organic FBs and vanadium FBs are discussed. Finally, the challenges and future directions of ML research in FBs are proposed.

A Heuristic Approach to Linking Experimental Descriptors with Product Selectivity in Electrochemical CO2 Reduction

An important challenge in electrochemical CO2 reduction (ECR) is relating experimental conditions to their consequences, particularly in terms of product selectivity. The problem lies in the lack of descriptors which adequately describe the experimental protocols and their associated results. In this study, a machine learning approach is applied to correlate the molar composition of 21 single metals and 23 bimetallic particles, as well as operating parameters, from a large collection of synthetic records compiled from the literature with product selectivity. The decision tree obtained shows the conditions that lead to high desired product selectivity and provides a heuristic insight into its electrochemistry. As such, the data does not provide details. However, machine learning algorithms are capable of identifying hidden patterns in the data, providing a deeper insight into the chemistry involved in product formation in the ECR.

Artificial Intelligence Applied to Battery Research: Hype or Reality?

This is a critical review of artificial intelligence/machine learning (AI/ML) methods applied to battery research. It aims at providing a comprehensive, authoritative, and critical, yet easily understandable, review of general interest to the battery community. It addresses the concepts, approaches, tools, outcomes, and challenges of using AI/ML as an accelerator for the design and optimization of the next generation of batteries—a current hot topic. It intends to create both accessibility of these tools to the chemistry and electrochemical energy sciences communities and completeness in terms of the different battery R&D aspects covered.

Material Design of Aqueous Redox Flow Batteries: Fundamental Challenges and Mitigation Strategies

Redox flow batteries (RFBs) are critical enablers for next-generation grid-scale energy-storage systems, due to their scalability and flexibility in decoupling power and energy. Aqueous RFBs (ARFBs) using nonflammable electrolytes are intrinsically safe. However, their development has been limited by their low energy density and high cost. Developing ARFBs with higher energy density, lower cost, and longer lifespan than the current standard is of significant interest to academic and industrial research communities. Here, a critical review of the latest progress on advanced electrolyte material designs of ARFBs is presented, including a fundamental overview of their physicochemical properties, major challenges, and design strategies. Assessment methodologies and metrics for the evaluation of RFB stability are discussed. Finally, future directions for material design to realize practical applications and achieve the commercialization of ARFB energy-storage systems are highlighted.

Densely Populated Bismuth Nanosphere Semi-Embedded Carbon Felt for Ultrahigh-Rate and Stable Vanadium Redox Flow Batteries

The elaborate spatial arrangement and immobilization of highly active electrocatalysts inside porous substrates are crucial for vanadium redox flow batteries capable of high-rate charging/discharging and stable operation. Herein, a type of bismuth nanosphere/carbon felt is devised and fabricated via the carbothermic reduction of nanostructured bismuth oxides. The bismuth nanospheres with sizes of ≈25 nm are distributed on carbon fiber surfaces in a highly dispersed manner and its density reaches up to ≈500 pcs µm^-2 , providing abundant active sites. Besides, a unique bismuth nanosphere semi-embedded carbon fiber structure with strong interfacial BiC chemical bonding is spontaneously formed during carbothermic reactions, offering an excellent mechanical stability under flowing electrolytes. It shows that the bismuth nanosphere semi-embedded carbon felt can effectively promote V(II)/V(III) redox reactions with appreciable catalytic activity. The battery with the present electrode sustains an energy efficiency of 77.1 ± 0.2% and an electrolyte utilization of 57.2 ± 0.2% even when a current density up to 480 mA cm^-2 is applied, which are remarkably higher than those of batteries with the bismuth nanoparticle/carbon felt synthesized by the electrodeposition method (62.6 ± 0.1%, 23.6 ± 0.2%). Further, the battery with the present electrode demonstrates a stable energy efficiency retention of 98.2% after 1000 cycles.