Machine learning discovers ‘hidden-gem’ materials for heat-free gas separation
Chemical separation, including gas separation, is a common process that is required for manufacturing and research. It accounts for a whopping 15 percent of U.S. energy consumption and produces millions of tons of carbon emissions.
Separating gases by passing them through membranes could be an efficient, environmentally friendly alternative to current methods — if only the right materials could be found to make them.
Applying a graph-based machine learning approach, a team of chemical and mechanical engineers and computer scientists at the University of Notre Dame have discovered, synthesized and tested polymer membranes that can separate gases up to 6.7 times more effectively than previously synthesized membranes. Their results have been published in Cell Reports Physical Science.
“What determines the membrane’s performance is the material’s microscopic porosity,” said Agboola Suleiman, doctoral student in the lab of Ruilan Guo, the Frank M. Freimann Collegiate Professor of Engineering.
“The ideal membrane material strikes a balance between selectivity and permeability — permeable enough to let gases in, but selective enough to keep some out,” said Suleiman, who is co-author on the paper.
To identify this Goldilocks material, the team used graph neural networks (GNN), a type of machine learning particularly well-suited to representing a material’s molecular structure as well as its relationship with other molecules. After being trained on datasets, GNN identified two polymers that had the right properties to outperform previously synthesized membranes.
“Our machine learning algorithms led us to materials that had previously only been used for electronics applications,” said Tengfei Luo, the Dorini Family Professor for Energy Studies, associate chair of the Department of Aerospace and Mechanical Engineering and co-author on the paper. “Then we synthesized and tested these materials in the lab, verifying their high performance in separating gases. It was like finding hidden gems.”
Synthesizing polymers can be costly and time-consuming, so the data available about their molecular structure and chemical properties are scarce and incomplete.
However, algorithmic innovations devised by co-authors and computer scientists Meng Jiang and his doctoral student Gang Liu solved this problem.
“By using machine learning techniques, we were able to augment and improve our data,” said Jiaxin Xu, doctoral student in Luo’s lab and co-author on the paper. “The graph-based model, enriched with information about each material’s molecular properties, allowed us not only to predict the best membrane materials but also to explain why they’re the best.”
The team’s top-performing polymers may be used to create membranes capable of separating several gas pairs, which are critical for industrial applications.
Latest ND NewsWire
- Notre Dame marks another year of unprecedented research successDuring the 2024 fiscal year, researchers at the University of Notre Dame submitted 1,310 proposals for external research funding for a total amount of $1.016 billion — the first time the University has surpassed the billion-dollar mark for proposals. In addition, the University received 829 separate awards — the largest number on record. With $223 million in total funding, these awards propelled the University past the $200 million mark for the fourth straight year.
- Notre Dame President Emeritus Rev. John I. Jenkins, C.S.C., visits key sites in Lviv, UkraineRev. John I. Jenkins, C.S.C., president emeritus of the University of Notre Dame, recently visited the Ukrainian Catholic University (UCU) and key sites in Lviv, Ukraine, as a sign of Notre Dame’s continued support for the university and its students. It was his first international trip on behalf of Notre Dame since stepping down from the presidency at the end of the 2023-24 academic year.
- Notre Dame partners to grow Indiana’s mental health workforceThe University of Notre Dame is part of a statewide effort to address the mental health workforce shortage. In partnership with WISE Indiana, the University is contracted to help enhance the recruitment, retention and quality of Indiana’s behavioral health workforce.
- Notre Dame ranked among state’s top employers by ForbesForbes magazine’s annual survey of America’s best in-state employers has ranked the University of Notre Dame the leading employer in Indiana’s education sector and second among all of the state’s large organizations. “Being…
- Virtual learning detrimental to school attendance, especially in districts with higher poverty rates, study findsSince the COVID-19 pandemic, rates of chronic absenteeism have nearly doubled across the nation for students in kindergarten through grade 12. This increase was tied to the mode of instruction during the early years of the pandemic. In particular, schools that employed virtual learning as the primary teaching mode during the 2020-21 school year experienced a greater increase in chronic absenteeism in the following year. That increase was significantly greater in school districts with higher levels of poverty, according to new research from William Evans, the Keough-Hesburgh Professor of Economics and co-founder of Notre Dame’s Wilson Sheehan Lab for Economic Opportunities.
- Alumni Association and YoungND honor 2024 Domer DozenThe Notre Dame Alumni Association announced its 2024 Domer Dozen cohort, honoring 12 graduates ages 32 and younger for excellence in their contributions in faith, service, learning or work — the core pillars of the association’s mission.