As the core component of flexible energy storage and electronic devices, the research and development of gel electrolyte has long been limited by the inefficiency of the traditional trial and error method in exploring the complex component structure performance relationship. The data-driven intelligent research and development paradigm is leading the field towards a rational acceleration stage of design validation by integrating high-throughput experiments, multi-scale computing, and artificial intelligence technology. This review systematically elaborates on the core methods, key challenges, and cutting-edge trends of this paradigm. At the methodological level, we focused on the construction of standardized databases (integrating literature data, high-throughput experiments, and molecular simulations), the establishment and application of machine learning models (such as graph neural networks for quantitative structure-activity relationship prediction and generative models for reverse engineering), and a closed-loop experimental design strategy centered on Bayesian optimization, aiming to synergistically optimize multiple properties such as ion conductivity, mechanical strength, and electrochemical window. The article deeply analyzes the core challenges currently faced, including the scarcity and heterogeneity of high-quality data, the lack of interpretability of complex models leading to difficulties in analyzing physical and chemical mechanisms, and the limitations of model migration and generalization between different electrolyte systems and performance indicators. Finally, we look forward to the cutting-edge development trends, including the cross scale prediction model integrating multi-scale simulation and experimental data, the autonomous laboratory to realize the automation of the whole process of design synthesis characterization optimization, and the construction of gel electrolyte digital twins to achieve life-cycle performance monitoring and optimization. The purpose of this review is to provide a clear roadmap for researchers in the cross field of materials science, electrochemistry and data science, and promote the research and development of gel electrolyte into a new era with data and intelligence as the core driving force. The core elements, key challenges and cutting-edge trends of data-driven methods in the intelligent research and development of gel electrolytes are systematically described, and the design verification closed-loop is constructed. • Deep fusion of experimental and computational data. • Building an intelligent electrolyte design core. • Overcoming data sparsity and migration bottlenecks. • Realize precise mapping of cross scale performance. • Moving towards a new paradigm of independent closed-loop research and development.
Ren et al. (Wed,) studied this question.