Convergence of Computational Materials Science and AI for Next-Generation Energy Storage Materials
Pan X. Xie Y. Li C. He Y. Zhang Y. Wang Y. Li Z. Peng P. Wang J.
January 2026Springer
Journal of Electronic Materials
2026#55Issue 145 - 114 pp.
With the urgent demand for high-performance energy storage materials in the global energy transition, traditional experimental trial and error methods are difficult to meet the rapid research and development needs owing to long cycles and high costs. In recent years, the deep integration of computational materials science and artificial intelligence (AI) technology has provided revolutionary tools for the rational design and performance optimization of energy storage materials. This article systematically reviews the progress of research on energy storage material computation and AI systems. At the traditional method level, quantum mechanics computation (such as VASP, Quantum ESPRESSO), molecular dynamics (such as LAMMPS, GROMACS), and high-throughput computing platforms (such as Materials Project) have achieved accurate predictions of material electronic structure, interface dynamics, and high-throughput screening. At the AI-driven level, generative models (GNoME, 3D-GPT), graph neural networks (MEGNet, CGCNN), and experimental computational closed–loop systems (such as the autonomous driving laboratory A-Lab) have significantly accelerated the discovery and reverse design of new materials. Further focusing on the integration trend of multi-scale modeling and AI, physical information-driven AI models (DPMD, PINNs) and cross-scale integration platforms (ASE, MedeA) are driving the collaborative improvement of material simulation accuracy and efficiency. However, data scarcity, computational bottlenecks caused by multi-physics coupling, and barriers to tool industrialization remain current challenges. In the future, sustainable design paradigms, open-source ecological construction, and human-machine collaboration models will lead the research and development of energy storage materials into the era of “digital priority.” This article aims to provide a technical roadmap reference for interdisciplinary research and call for collaboration between academia and industry to overcome key bottlenecks and accelerate the innovation breakthrough and large-scale application of energy storage materials.
artificial intelligence , Energy storage materials , high-throughput computing , material genomics , multi-scale simulation
Text of the article Перейти на текст статьи
Zhongshan Advanced New Functional Materials Engineering Technology Research Center, Zhongshan Polytechnic, Zhongshan, 528400, China
Laboratory of Functional Nanomaterials, Institute of Combustion Problems, Al-Farabi Kazakh National University, Bogenbay Batyr Str. 1721, Almaty, 050012, Kazakhstan
Faculty of Chemical Technology, Poznan University of Technology, Berdychowo 4, Poznan, 60965, Poland
School of Energy Science and Technology, Henan University, Kaifeng, 475004, China
Faculty of Chemistry and Chemical Technology, Al-Farabi Kazakh National University, 71 al-Farabi Ave., Almaty, 050040, Kazakhstan
Zhongshan Advanced New Functional Materials Engineering Technology Research Center
Laboratory of Functional Nanomaterials
Faculty of Chemical Technology
School of Energy Science and Technology
Faculty of Chemistry and Chemical Technology
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026