Proceedings of MATSUS Spring 2024 Conference (MATSUS24)
DOI: https://doi.org/10.29363/nanoge.matsus.2024.319
Publication date: 18th December 2023
Unlimited access to clean, sustainable and renewable source of energy seems to be a dream scenario, however with an assistance of machine learning (ML) approach the experimental work which actually reveals the right descriptors may gain a powerful tool allowing to omit a time consuming trials path. As a matter of fact, the ML has already shown the potential to significantly reduce the time and effort required for developement of new and efficient photocatalysts.
However, precise definition of descriptors will require an identification of the bottleneck materials parameters, features and processes, thus different architectures and working arrangements will be shown and disscused in this presentation in order to test their usfulness for prediction of novel and better arrangements for hydrogen and other carbon based solar fuels production.
Over 400 samples based on the semiconductor oxides have been prepared and measured in order to bulid a pre-base for ML tests. Different materials and working systems, their compositions, geometry, properties will be disscused in view of their impact on the final prediction. In this presentation we will discuss the strengths and weaknesses of different architectures and working arrangements for hydrogen and carbon-based solar fuels production.