Solar fuel technologies are capable of using components which are naturally abundant in our environment such as sunlight, carbon dioxide, nitrogen, and water for producing fuels. One important component in solar fuel technologies is a light absorbing material. It is crucial to find an appropriate material which can absorb maximum sunlight while undergoing minimal degradation to increase the efficiency of the solar fuel technology. This database including millions of optical, sheet resistance, composition, XRD, and Raman measurements for thousands of materials can accelerate research and development into solar fuel technologies.
Accelerating solar fuel R&D with machine learning
Machine learning algorithms in combination with novel experimental data can accelerate the process of materials design and discovery for solar fuels applications. Using machine learning algorithms on experimental data we can discover new materials which can serve as better light absorbers and/or catalysts, get ‘materials recipes’ for synthesizing materials, and build tools to automatically analyze new measurements to retrieve insights. This could help design new solar fuels with higher efficiencies which will greatly affect the solar fuel industry.
See what’s been done with machine learning for solar fuels: