Generalized BEP Relationships for the Prediction of Activation Energies via Machine Learning

Case ID:

At the heart of computational catalyst design lies the construction of a suitable reaction network and the determination of reaction and activation energies for each step for a specific set of, for instance, metals. This technology aims to enable the creation of a sophisticated activation energy predictor / modeler that will enable the investigation and development of chemical reactions through an optimized catalyst.

Utilizing machine learning, this technology seeks to revolutionize the catalyst design process by drawing from vast datasets to make more informed decisions. This holistic approach ensures that researchers can hone in on the most effective catalysts without the intensive time investments traditionally required.

Current methods require sophisticated teams working iteratively with best guesses to develop an optimized reaction. This technology aims to significantly improve the workflow for these teams by many magnitudes. Improving the number of options being analyzed and solving more problems and applications. While previously the identification of more efficient catalysts relied on the intuition of researchers in selecting and evaluating a small number of new compounds for a given reaction. However, today large search spaces can be screened using descriptor-based approaches obtained from computational work alone.

With the integration of machine learning, the reliance on human intuition diminishes, paving the way for more systematic and data-driven evaluations. This shift not only accelerates the research process but also eliminates potential human biases, ensuring that the most viable catalyst options are consistently brought to the forefront.


  • Chemical industry
  • Pharmaceutical research
  • Biochemical process optimization


  • Greater efficiency
  • Cost savings
  • Predictive 
  • Accelerated research timeline
  • Consistency in catalyst evaluation
Patent Information:
Contact For More Information:
Tariq Ahmed
Sr Licensing Manager, College of Engineering
The University of Arizona
Lead Inventor(s):
Florian Goeltl