In this work, we develop a deep neural network model for the reaction rate of oxidative coupling of methane from published high-throughput experimental catalysis data. A 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/SiO2at different temperatures and to identify new catalysts and combinations 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
The generation of reference data for deep learning models is challenging for reactive systems, and more so for combustion reactions due to the extreme conditions that create radical species and alternative spin states during the combustion process. Here, we extend intrinsic reaction coordinate (IRC) calculations with
- Award ID(s):
- 1955643
- NSF-PAR ID:
- 10367440
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Scientific Data
- Volume:
- 9
- Issue:
- 1
- ISSN:
- 2052-4463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
A deep neural network for oxidative coupling of methane trained on high-throughput experimental datamore » « less
Abstract x /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 C2compared 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 C2products. This study demonstrates the value of learning a deep neural network model for 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. -
more » « less
Abstract This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While most contemporary symmetry-aware models use invariant convolutions and only act on scalars, NequIP employs E(3)-equivariant convolutions for interactions of geometric tensors, resulting in a more information-rich and faithful representation of atomic environments. The method achieves state-of-the-art accuracy on a challenging and diverse set of molecules and materials while exhibiting remarkable data efficiency. NequIP outperforms existing models with up to three orders of magnitude fewer training data, challenging the widely held belief that deep neural networks require massive training sets. The high data efficiency of the method allows for the construction of accurate potentials using high-order quantum chemical level of theory as reference and enables high-fidelity molecular dynamics simulations over long time scales.
-
We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces. With the advantage of directional information from trainable force vectors, and physics-infused operators that are inspired by Newtonian physics, the entire model remains rotationally equivariant, and many-body interactions are inferred by more interpretable physical features. We test NewtonNet on the prediction of several reactive and non-reactive high quality ab initio data sets including single small molecules, a large set of chemically diverse molecules, and methane and hydrogen combustion reactions, achieving state-of-the-art test performance on energies and forces with far greater data and computational efficiency than other deep learning models.more » « less
-
null (Ed.)Standard enthalpies, entropies, and heat capacities are calculated for more than 14,000 halogenated species using a high-fidelity automated thermochemistry workflow. This workflow generates conformers at density functional tight binding (DFTB) level, optimizes geometries, calculates harmonic frequencies, and performs 1D hindered rotor scans at DFT level, and computes electronic energies at G4 level. The computed enthalpies of formation for 400 molecules show good agreement with literature references, but the majority of the calculated species have no reference in the literature. Thus, this work presents the most accurate thermochemistry for many halogenated hydrocarbons to date. This new dataset is used to train an extensive ensemble of group additivity values (GAV) and hydrogen bond increment groups (HBI) within the Reaction Mechanism Generator (RMG) framework. On average, the new group values estimate standard enthalpies for halogenated hydrocarbons within 3 kcal/mol of their G4 values. To demonstrate the significance of RMG’s improved halogen thermochemistry, a model for C3H2F3Br (2-BTP) is generated, and flame speeds are compared to a literature mechanism. A significant contribution towards the automation of detailed modeling of halogenated hydrocarbon combustion, this research provides thermochemical data for thousands of novel halogenated species and presents a comprehensive set of halogen group additivity values.more » « less
-
more » « less
Abstract The prediction of temperature effects from first principles is computationally demanding and typically too approximate for the engineering of high-temperature processes. Here, we introduce a hybrid approach combining zero-Kelvin first-principles calculations with a Gaussian process regression model trained on temperature-dependent reaction free energies. We apply this physics-based machine-learning model to the prediction of metal oxide reduction temperatures in high-temperature smelting processes that are commonly used for the extraction of metals from their ores and from electronics waste and have a significant impact on the global energy economy and greenhouse gas emissions. The hybrid model predicts accurate reduction temperatures of unseen oxides, is computationally efficient, and surpasses in accuracy computationally much more demanding first-principles simulations that explicitly include temperature effects. The approach provides a general paradigm for capturing the temperature dependence of reaction free energies and derived thermodynamic properties when limited experimental reference data is available.
