Machine learning advances materials for separations, adsorption and catalysis

Metal-organic structures (MOFs) are a class of porous and crystalline materials that are synthesized from inorganic metal ions or clusters attached to organic ligands. Two of these materials are shown, HKUST-1 and MIL-100 (Fe). (Credit: Tania Evans, Georgia Tech)

An artificial intelligence technique, machine learning, is helping to accelerate the development of highly tunable materials known as metal-organic structures (MOFs) that have important applications in chemical separations, adsorption, catalysis and sensing.

Using property data from over 200 existing MOFs, the machine learning platform has been trained to guide the development of new materials by predicting an often essential property: water stability. Using model guidance, researchers can avoid the lengthy task of synthesizing and then experimentally testing new candidate MOFs for their aqueous stability. Researchers are already expanding the model to predict other important MOF properties.

Supported by the Office of Science’s Basic Energy Sciences program within the United States Department of Energy (DOE), the research was published November 9 in the journal Nature Machine Intelligence. The research was conducted in the Center for Understanding and Control of Acid Gas-Induced Evolution of Materials for Energy (UNCAGE-ME), a DOE Energy Frontier Research Center located at the Georgia Institute of Technology.

“The water stability problem with MOFs has existed for a long time in this field, with no easy way to predict it,” said Krista Walton, professor and member of Robert “Bud” Moeller’s faculty at Georgia Tech’s School of Chemical. and Biomolecular Engineering. “Instead of having to synthesize and experiment to figure it out for each candidate MOF, this machine learning model now provides a way to predict water stability given a set of desired characteristics. This will really speed up the process of identifying new materials for specific applications. “

MOFs are a class of porous, crystalline materials that are synthesized from inorganic metal ions or clusters attached to organic ligands. They are known for their easily tunable components that can be customized for specific applications, but the large number of potential combinations makes it difficult to choose MOFs with the desired properties. This is where artificial intelligence can help.

Machine learning is playing an increasingly important role in materials science, said Rampi Ramprasad, professor and Michael E. Tennenbaum Family Chair at the Georgia Tech School of Materials Science and Engineering and Georgia Research Alliance Eminent Scholar in Energy Sustainability.

“When materials scientists plan the next set of experiments, we use the intuition and insights we have accumulated from the past,” Ramprasad said. “Machine learning allows us to take full advantage of this knowledge of the past in the most efficient and effective way. If 200 experiments have already been done, machine learning allows us to take advantage of everything that has been learned from them as we plan the 201st. experiment “.