Towards Machine Learning in Heterogeneous Catalysis-A Case Study of 2,4-Dinitrotoluene Hydrogenation.

Alexandra Jakab-Nácsa, Attila Garami, Béla Fiser, László Farkas, Béla Viskolcz

International journal of molecular sciences 2023 Jul 14

filter terms:

case study (1)

catalysis (3)

data analysis (2)

research (1)

Sizes of these terms reflect their relevance to your search.

Utilization of multivariate data analysis in catalysis research has extraordinary importance. The aim of the MIRA21 (MIskolc RAnking 21) model is to characterize heterogeneous catalysts with bias-free quantifiable data from 15 different variables to standardize catalyst characterization and provide an easy tool to compare, rank, and classify catalysts. The present work introduces and mathematically validates the MIRA21 model by identifying fundamentals affecting catalyst comparison and provides support for catalyst design. Literature data of 2,4-dinitrotoluene hydrogenation catalysts for toluene diamine synthesis were analyzed by using the descriptor system of MIRA21. In this study, exploratory data analysis (EDA) has been used to understand the relationships between individual variables such as catalyst performance, reaction conditions, catalyst compositions, and sustainable parameters. The results will be applicable in catalyst design, and using machine learning tools will also be possible.

Citation

Alexandra Jakab-Nácsa, Attila Garami, Béla Fiser, László Farkas, Béla Viskolcz. Towards Machine Learning in Heterogeneous Catalysis-A Case Study of 2,4-Dinitrotoluene Hydrogenation. International journal of molecular sciences. 2023 Jul 14;24(14)