.png){kind=icon}
.png){kind=icon}
Return
Role of artificial intelligence in the design and discovery of next-generation battery electrolytes
.png){kind=icon}
OA
AI
M
T
DOI：10.1063/5.0251325.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Adverse climate change, global warming, and energy security have emerged as global challenges, demanding advancements in high-performance battery technologies to drive sustainability. In this scenario, developing electrolytes has gained significant momentum among various innovations, given their critical role in determining battery safety and performance. However, the conventional trial-and-error approach to electrolyte discovery is costly, complex, time-consuming, and often inefficient. Recent advancements in artificial intelligence (AI) over the past decade have catalyzed innovations across diverse fields, ranging from nanotechnology to space explorations, and are now emerging as a powerful tool for materials discovery. Numerous studies have demonstrated the effectiveness of AI in screening and characterizing next-generation electrolytes. This review offers a comprehensive outlook on the transformative role of AI in designing novel electrolytes. Examination of various electrolytes and their key parameters that influence the electrochemical performance of batteries is conducted. The challenges and opportunities in using AI to design electrolytes with tailored properties are explored. Furthermore, a futuristic vision for integrating science-driven AI-based approaches with existing experimental and theoretical methods to accelerate electrolyte discovery is presented. By offering such a comprehensive understanding, this review aims to provide researchers, industries, and policymakers with insights into how AI can be leveraged to design next-generation electrolytes, paving the way toward transformative progress in battery technology.
Keywords:
LITHIUM-ION BATTERIES
LI-ION
TRIMETHYL PHOSPHATE
STATE
TRANSPORT
TEMPERATURE
MECHANISMS
PREDICTION
CAPACITY
FIRE
Journal
IF:
6.2
Papers:
192
Citations:
717
Organization
B
Cited Papers