Materials synthesis and science have witnessed a number of paradigm shifts over the last decades. The initial progress was largely empirical, trial-and-error based with minimal understanding of the physical principles governing material behavior. The development of theoretical models, combined with advances in computational power, enabled the simulation of complex synthesis processes. Over the last few years, artificial intelligence (AI) has started to revolutionize the field with the promise of data-driven discovery and automation of materials design. 

My PhD project at the LRCS, CNRS builds directly upon this trajectory. It focuses on the development of machine learning models that correlate synthesis protocols with resulting material properties and on using multi-objective Bayesian optimization to inversely design protocols that meet desired property targets. The models are employed specifically for Redox Flow Batteries (RFBs).

The broader vision of my work is self-driving laboratories. This reflects the next frontier in materials innovation, where artificial intelligence is no longer just a tool but a collaborator in accelerating sustainable energy storage solutions. This project will directly assist in the digitalization of battery research and the acceleration of next-generation material discovery.