A deep neural network for oxidative coupling of methane trained on high-throughput experimental data

Abstract

In this work, we develop a deep neural network model of the reaction rate of oxidative coupling of methane from published high-throughput experimental catalysis data. The neural network is formulated so that the rate model satisfies the plug flow reactor design equation. The model is then employed to understand the variation of reactant and product composition within the reactor for the reference catalyst Mn−Na2WO4/SiO2 at different temperatures and to identify new catalysts and combination of known catalysts that would increase yield and selectivity relative to the reference catalyst. The model revealed that methane is converted in the first half of the catalyst bed while the second part largely consolidates the products (i.e. increases ethylene to ethane ratio). A screening study of ≥ 3400 combinations of pairs of previously studied catalysts of the form M1(M2)1−2M3Ox/support (where M1, M2, and M3 are metals) revealed that a reactor configuration comprising two sequential catalyst beds leads to synergistic effects resulting in increased yield of C2 compared to the reference catalyst at identical conditions and contact time. Finally, an expanded screening study of 7400 combinations (comprising previously studied metals but with several new permutations) revealed multiple catalyst choices with enhanced yields of C2 products. This study shows the value of learning a deep neural network model of the instantaneous reaction rate directly from high throughput data and represents a first step in constraining a data-driven reaction model to satisfy domain information.

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

“…The desired metrics are more like composite functions of these directly measurable and well-defined quantities, and obtaining empirically a general form for the relevant equations is often not straightforward and can require significant expert knowledge and experience. Thankfully, a variety of other methods have built on or expanded beyond the original approach to incorporate information on chemical kinetics, [112,115,116] thermochemical/thermophysical information, [115,[117][118][119][120] mass/energy balances, [121][122][123] reactor engineering dynamics, [124,125] computed interatomic potentials, [126] and optics. [127] Many of these expanded approaches enable embedding of chemical information and may no longer be restricted to only finding solutions to and/or fitting PDEs with a previously known form.…”

“…Thankfully, a variety of other methods have built on or expanded beyond the original approach to incorporate information on chemical kinetics, [ 112 , 115 , 116 ] thermochemical/thermophysical information, [ 115 , 117 , 118 , 119 , 120 ] mass/energy balances, [ 121 , 122 , 123 ] reactor engineering dynamics, [ 124 , 125 ] computed interatomic potentials, [ 126 ] and optics. [ 127 ] Many of these expanded approaches enable embedding of chemical information and may no longer be restricted to only finding solutions to and/or fitting PDEs with a previously known form.…”

Model-Based Catalyst Screening and Optimal Experimental Design for the Oxidative Coupling of Methane

“…Also, random forest regressors learn via decision thresholds on descriptors to segment the design space in which aggregate predictions are made, making it agnostic to scale of the features and eliminating the need for much data pre-processing. When highly parametrized set of ML models like neural networks that run the risk of overfitting to the artefacts in data is used, good pre-processing, efforts to embed the training with mass balances, and even truncation of datapoints with mass balance violation beyond a fixed threshold have been widely considered [22,26].…”