A system that uses machine learning to speed up the search for materials for renewable energy technologies has been developed by researchers. They found and successfully synthesized two new candidate materials for use in solid oxide fuel cells, which are machines that produce energy from fuels that don’t emit carbon dioxide, like hydrogen.
Accelerating the search for other novel materials beyond the energy industry may also be possible with the help of research findings from Kyushu University published in the journal Advanced Energy Materials, which were obtained through collaboration with Osaka University and the Fine Ceramics Center.
As the planet warms, scientists are creating novel methods of producing energy without the use of fossil fuels. Establishing a hydrogen society is one way to achieve carbon neutrality. But we also need to increase the power-generating efficiency of hydrogen fuel cells in addition to streamlining the production, storage, and transportation of hydrogen, says Professor Yoshihiro Yamazaki of Kyushu University’s Department of Materials Science and Technology, Platform of Inter-/Transdisciplinary Energy Research (Q-PIT).
Solid oxide fuel cells must be able to effectively conduct hydrogen ions, also known as protons, through a solid substance called an electrolyte in order to produce an electric current. Currently, oxides with extremely particular atom crystal arrangements—known as perovskite structures—are the subject of research into novel electrolyte materials.
According to Professor Yamazaki, “new high-performing perovskites are continually being reported.” The first proton-conducting oxide was found in a perovskite structure. But since non-perovskite oxides can also conduct protons very effectively, we wish to broaden the scope of solid electrolyte discovery.
However, using conventional “trial and error” approaches to find proton-conducting materials with different crystal structures has many drawbacks. Tiny amounts of an additional material, referred to as a dopant, must be added to the base material in order for an electrolyte to acquire the capacity to carry protons. But it becomes challenging and time-consuming to identify the ideal combination that improves proton conductivity since there are so many interesting base and dopant options, each with unique atomic and electronic properties.
Rather, the scientists computed the characteristics of several oxides and dopants. They then analyzed the data, determined the variables influencing a material’s proton conductivity, and made predictions about possible combinations using machine learning.
The scientists then created two intriguing materials, each with a distinct crystal structure, and evaluated how well they carried protons, all under the guidance of these variables. Notably, in a single experiment, both materials showed proton conductivity.
The first known proton conductor with a sillenite crystal structure is one of the materials, the researchers noted. The high-speed proton conduction path of the other, with a eulytite structure, is different from the conduction paths observed in perovskites. These oxides don’t work well as electrolytes at the moment, but the research team thinks that if they are studied more, they will become more conductible.
“Our framework has the potential to significantly accelerate the development of solid oxide fuel cells by broadening the search space for proton-conducting oxides.” Professor Yamazaki says, “It’s a promising step toward realizing a hydrogen society.” “This framework could potentially speed up the development of many novel materials with minor modifications and be applied to other fields of materials science as well.”
