Sodium-ion batteries (SIBs) are regarded as promising next-generation energy storage systems, benefiting from the abundant reserves and low cost of sodium resources. However, safety hazards and performance bottlenecks originating from electrolytes, anodes, and cathodes have not only led to frequent accidents but also severely hindered their industrialization process. Current review works, which mainly focus on isolated issues or single components, lack the holistic guidance required for the development of high-safety and high-performance SIBs. To fill this research gap, this review systematically summarizes the latest advances in the application of machine learning (ML) in SIBs development from the perspective of core components. First, we clarify the root causes of key challenges for each component, and then evaluate the role of ML in accelerating material discovery, optimizing electrochemical performance, and mitigating safety risks. Specifically, ML methodologies such as graph neural networks, multi-objective optimization, and physics-informed models are highlighted for their unique advantages in deciphering the structure-performance relationships of SIBs materials. This work demonstrates that ML can efficiently explore the high-dimensional design spaces of electrodes and electrolytes, thereby establishing a data-driven paradigm for SIBs optimization. Finally, we propose that future research should prioritize the construction of standardized data ecosystems, the development of integrated computational-experimental pipelines, and the establishment of cross-component safety design frameworks, aiming to bridge the gap between computational predictions and practical industrial applications.

Aluminum (Al) metal is a promising anode material for rechargeable aluminum batteries (RABs) due to its high abundance and specific capacity. However, its application is limited by dendrite formation and ultra-thick separators are usually required. Here, we propose that silica nanoparticles (nano-SiO₂) can serve as multifunctional additive for chloroaluminate electrolyte (IL) because of their unique physicochemical properties. By combining experimental and simulation studies, nano-SiO₂ form a colloidal system with IL, which helps nano-SiO₂ play a positive role throughout battery lifecycle. They help to uniform electric field, increase ion migration number, and promote electrochemical reactions on the anode side, which inhibits the growth of Al dendrite and enhances the cycle life of battery. By using IL-SiO₂-3‰, the cycle life of the symmetric cell increases to 2300 h at 1 mA·cm⁻², which is approximately 80 times greater than that using IL. The cycle number of the Al//graphite full battery increases from 3644 in IL to over 26,000 in IL-SiO₂-3‰ at 2 A·g⁻¹ with a capacity retention of ~ 99%. This work provides a valuable direction for the further optimization of the interface between metal anode and electrolyte in rechargeable batteries.

The development of non-platinum group metal (non-PGM) and efficient multifunctional electrocatalysts for oxygen reduction reaction (ORR), oxygen evolution reaction (OER), and hydrogen evolution reaction (HER) with high activity and stability remains a great challenge. Herein, by in-situ transforming silver manganese composite oxide heterointerface into boosted Mott–Schottky heterointerface through a facile carbon reduction strategy, a nanorod-like silver/manganese oxide with superior multifunctional catalytic activities for ORR, OER and HER and stability was obtained. The nanorod-like silver/manganese oxide with Mott–Schottky heterointerface (designated as Ag/Mn₃O₄) exhibits an ORR half-wave potential of 0.831 V (vs. RHE) in 0.1 M KOH, an OER overpotential of 338 mV and a HER overpotential of 177 mV at the current density of 10 mA·cm⁻² in 1 M KOH, contributing to its noble-metal benchmarks comparable performance in aqueous aluminum-air (Al-air) battery and laboratorial overall water splitting electrolytic cell. Moreover, in-situ electrochemical Raman and synchrotron radiation spectroscopic measurements were conducted to further illustrate the catalytic mechanism of Ag/Mn₃O₄ Mott–Schottky heterointerface towards various electrocatalytic reactions. At the heterointerface, the Ag phase serves as the electron donor and the active phase for ORR and HER, while the Mn₃O₄ phase serves as the electron acceptor and the active phase for OER, respectively. This work deepens the understanding of the Mott–Schottky effect on electrocatalysis and fills in the gap in fundamental physical principles that are behind measured electrocatalytic activity, which offers substantial implications for the rational design of cost-effective multifunctional electrocatalysts with Mott–Schottky effect.