| Autor: |
Guoqing Wang, Zongmin Luo, Halefom G. Desta, Mu Chen, Yingchao Dong, Bin Lin |
| Jazyk: |
angličtina |
| Rok vydání: |
2025 |
| Předmět: |
|
| Zdroj: |
Energy Reviews, Vol 4, Iss 1, Pp 100106- (2025) |
| Druh dokumentu: |
article |
| ISSN: |
2772-9702 |
| DOI: |
10.1016/j.enrev.2024.100106 |
| Popis: |
Energy drives the development of human civilization, and hydrogen energy is an inevitable choice under the goal of “global energy transition”. As hydrogen technology continues to advance, solid-state hydrogen storage materials have garnered significant attention as an efficient solution for hydrogen energy storage. However, existing research methods, such as experimental preparation and theoretical calculations, are inefficient and costly. Here, we summarize the latest advancements of high-throughput screening (HTS) and machine learning (ML) solid-state hydrogen storage materials. We elaborate on the advantages of HTS and ML in rapid material screening, performance assessment and prediction, and so on. We place particular emphasis on the exploration and analysis of research progress involving the application of HTS and ML in various types of solid-state hydrogen storage materials. Additionally, we discuss the advantages of integrating HTS and ML, emphasizing the application of this comprehensive strategy in solid-state hydrogen storage. In the realm of hydrogen storage, artificial intelligence plays a dual role. It not only enhances the efficiency of material screening but also offers novel research tools for future material design and development. This will aid in the discovery of new-type high-performance solid-state hydrogen storage materials and facilitate their rapid commercialization and practical application. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
