Energy materials play an important role in renewable and green energy technologies. The exploration of new materials, including nanomaterials, is important for breaking through the current bottlenecks of energy density and charging rates. However, traditional theoretical computational methods face the dilemma of long research cycles. Machine learning methods have in recent years shown considerable potential for accelerating research efforts. However, most approaches are limited to specific properties of particular devices. In this paper, we propose a forward prediction and screening framework for functional materials, which includes database selection, attributes, descriptors, machine learning models, and prediction and screening. Based on the Materials Project database, auto-encoding methods are employed to generate Coulomb matrices as the input to train the convolutional neural networks, which finally screen 12 lithium-ion, 6 zinc-ion, and 8 aluminum-ion battery cathode materials satisfying the criteria from 4,300 materials. The results show that the proposed framework can predict material performance well toward rapid initial screening. The proposed framework can provide a specific and complete working process reference for energy materials design work, contributing to the theoretical foundation for the design of core industrial software for materials engineering.

Increasing electrode thickness can substantially enhance the specific energy of lithium-ion batteries; however, ionic transport, electronic conductivity, and ink rheology are current barriers to adoption. Here, a novel approach using a mixed xanthan gum and locust bean gum binder to construct ultra-thick electrodes is proposed to address above issues. After combining aqueous binder with single-walled carbon nanotubes (SWCNT), active material (LiNi_0.8Co_0.1Mn_0.1O₂) and subsequent vacuum freeze-drying, highly aligned, and low-tortuosity structures with a porosity of ca. 50% can be achieved with an average pore size of 10 μm, whereby the gum binder-SWCNT-NMC811 forms vertical structures supported by tissue-like binder/SWCNT networks allowing for excellent electronic conducting phase percolation. As a result, ultra-thick electrodes with a mass loading of about 511 mg cm⁻² and 99.5 wt% active materials have been demonstrated with a remarkable areal capacity of 79.3 mAh cm⁻², which is the highest value reported so far. This represents a >25× improvement compared with conventional electrodes with an areal capacity of about 3 mAh cm⁻². This route also can be expanded to other electrode materials, such as LiFePO₄ and Li₄Ti₅O₁₂, and thus opens the possibility for low-cost and sustainable ultra-thick electrodes with increased specific energy for future lithium-ion batteries.