A Machine Learning Model for Identifying New Compounds to Fight Against Global Warming

Apr 19, 2023

By Kaitlyn Landram

Among all greenhouse gases, carbon dioxide is the highest contributor to global warming. If we do not take action by 2100, according to the Intergovernmental Panel on Climate Change, the average temperature of our world will increase by about 34 degrees Fahrenheit. Finding effective ways to capture and store CO₂ has been a challenge for researchers and industries focused on combating global warming, and Amir Barati Farimani has been working to change that.

"Machine learning models bear the promise for discovering new chemical compounds or materials to fight against global warming," explains Barati Farimani, an assistant professor of mechanical engineering at Carnegie Mellon University. "Machine learning models can achieve accurate and efficient virtual screening of CO₂ storage candidates and may even generate preferable compounds that never existed before."

Barati Farimani has made a breakthrough using machine learning to identify ionic liquid molecules. Ionic liquids (ILs) are families of molten salt that remain in a liquid state at room temperature, have high chemical stability and high CO₂ solubility, making them ideal candidates for CO₂ storage. The combination of ions largely determines the properties of ILs. However, such combinatorial possibilities of cations and anions make it extremely challenging to exhaust the design space of ILs for efficient CO₂ storage through conventional experiments.

Machine learning is often used in drug discovery to create so-called molecular fingerprints alongside graph neural networks (GNNs) that treat molecules as graphs and use a matrix to identify molecular bonds and related properties. For the first time, Barati Farimani has developed both fingerprint-based ML models and GNNs that are able to predict the CO₂ absorption in ionic liquids.

"Our GNN method achieves superior accuracy in predicting the CO₂ solubility in ion liquids," states Barati Farimani. "Unlike previous ML methods that rely on handcrafted features, GNN directly learns the features from molecular graphs."

Click here to see more...

Video: Independent Seed, National Impact | On The Brink: Episode 9

A survey of 200 independent seed businesses reveals what Canada's seed sector actually contributes — and what it stands to lose.

On the Brink, Justin Funk, a third-generation agri-marketer, shares the findings of a national survey conducted in early 2026. The numbers reframe the conversation: independent seed companies in Canada represent upwards of $1.7 billion in dedicated seed infrastructure, approximately 3,000 full-time equivalent jobs in rural communities, and an estimated $20 million in annual community contributions. And roughly 90% of Canada's cereals, pulses, and other small pollinated crops flow through them.

The survey also asked how dependent these businesses are on public plant breeding to survive. The answer was unambiguous. For policymakers evaluating the future of publicly funded breeding programs, Funk argues the economic case for this sector and the case for public plant breeding are the same argument.

On the Brink is a cross-country video series exploring the future of plant breeding in Canada. Each episode features voices from across the industry in an open, ongoing conversation about innovation and long-term investment in Canadian agriculture.