Identifying Descriptors for Promoted Rhodium-Based Catalysts for Higher Alcohol Synthesis via Machine Learning

Abstract

Rhodium-based catalysts offer remarkable selectivities toward higher alcohols, specifically ethanol, via syngas conversion. However, the addition of metal promoters is required to increase reactivity, augmenting the complexity of the system. Herein, we present an interpretable machine learning (ML) approach to predict and rationalize the performance of Rh-Mn-P/SiO 2 catalysts (P = 19 promoters) using the open-source dataset on Rh-catalyzed higher alcohol synthesis (HAS) from Pacific Northwest National Laboratory (PNNL). A random forest model trained on this dataset comprising 19 alkali, transition, post-transition metals, and metalloid promoters, using catalytic descriptors and reaction conditions, predicts the higher alcohols space-time yield (STY HA ) with an accuracy of R 2 = 0.76. The promoter's cohesive energy and alloy formation energy with Rh are revealed as significant descriptors during posterior feature-importance analysis. Their interplay is captured as a dimensionless property, coined promoter affinity index (PAI), which exhibits volcano correlations for space-time yield. Based on this descriptor, we develop guidelines for the rational selection of promoters in designing improved Rh-Mn-P/SiO 2 catalysts. This study highlights ML as a tool for computational screening and performance prediction of unseen catalysts and simultaneously draws insights into the property−performance relations of complex catalytic systems.

Identifying Catalyst Property Descriptors for CO2 Hydrogenation to Methanol via Big-Data Analysis

“…Owing to the powerfulness of modern computers and software, various Big-Data analysis approaches have been applied for identifying key descriptors governing catalyst performance in several reactions. − Very recently, Suvarna et al used a machine-learning approach to predict the space time yield of methanol formation in CO 2 hydrogenation. Expectedly, the gas hourly space velocity, total pressure, temperature, and amount of catalytically active metal were identified as the main parameters.…”

A Surrogate Machine Learning Model for the Design of Single-Atom Catalyst on Carbon and Porphyrin Supports towards Electrochemistry

“…15 Trained ML algorithms can then be used for predicting the optimal SAC with high activity and also for performing feature importance analysis and introducing new descriptors. 16,17 Subsequently, optimized SACs can be used for the desired electrochemical reaction for metal−air batteries and for producing valuable chemicals and fuels. Although ML has recently been used to predict the properties of SACs, 18−21 it is still in an early stage.…”

“…To address these issues, machine learning (ML), as a data-intensive tool, provides researchers the ability to accelerate time-consuming DFT calculations to predict the catalytic activity in a large parameter space of SACs. , For example, the DFT-predicted data along with input features are previously applied to train ML algorithms . Trained ML algorithms can then be used for predicting the optimal SAC with high activity and also for performing feature importance analysis and introducing new descriptors. , Subsequently, optimized SACs can be used for the desired electrochemical reaction for metal–air batteries and for producing valuable chemicals and fuels. Although ML has recently been used to predict the properties of SACs, − it is still in an early stage .…”

The promotional role of Mn in CO2 hydrogenation over Rh-based catalysts from a surface organometallic chemistry approach

“…However, to steer product selectivity towards oxygenates, promoters such as Mn and Fe have been intensively investigated. [7][8][9][10][11] However, understanding the role of these promoters at a molecular level has been challenging due to the ill-defined structure of these catalysts. To address the complex structure of heterogeneous catalysts, surface organometallic chemistry combined with thermolytic molecular precursors (SOMC/TMP) has emerged as a promising approach to construct well-defined model catalysts with tailored composition and interfaces.…”