Enhancing Activation Energy Predictions under Data Constraints Using Graph Neural Networks

Accurately predicting activation energies is crucial for understanding chemical reactions and modeling complex reaction systems. However, the high computational cost of quantum chemistry methods often limits the feasibility of large-scale studies, leading to a scarcity of high-quality activation energy data. In this work, we explore and compare three innovative approaches (transfer learning, delta learning, and feature engineering) to enhance the accuracy of activation energy predictions using graph neural networks, specifically focusing on methods that incorporate low-cost, low-level computational data. Using the Chemprop model, we systematically evaluated how these methods leverage data from semiempirical quantum mechanics (SQM) calculations to improve predictions. Delta learning, which adjusts low-level SQM activation energies to align with high-level CCSD(T)-F12a targets, emerged as the most effective method, achieving high accuracy with substantially reduced data requirements. Notably, delta learning trained with just 20-30% of high-level data matched or exceeded the performance of other methods trained with full data sets, making it advantageous in data-scarce scenarios. However, its reliance on transition state searches imposes significant computational demands during model application. Transfer learning, which pretrains models on large data sets of low-level data, provided mixed results, particularly when there was a mismatch in the reaction distributions between the training and target data sets. Feature engineering, which involves adding computed molecular properties as input features, showed modest gains, particularly in thermodynamic properties. Our study highlights the trade-offs between accuracy and computational demand in selecting the best approach for enhancing activation energy predictions. These insights provide valuable guidelines for researchers aiming to apply machine learning in chemical reaction engineering, helping to balance accuracy with resource constraints.

Tailoring parameters for QM/MM simulations: accurate modeling of adsorption and catalysis in zirconium-based metal-organic frameworks

Quantum mechanics/molecular mechanics (QM/MM) simulations offer an efficient way to model reactions occurring in complex environments. This study introduces a specialized set of charge and Lennard-Jones parameters tailored for electrostatically embedded QM/MM calculations, aiming to accurately model both adsorption processes and catalytic reactions in zirconium-based metal-organic frameworks (Zr-MOFs). To validate our approach, we compare adsorption energies derived from QM/MM simulations against experimental results and Monte Carlo simulation outcomes. The developed parameters showcase the ability of QM/MM simulations to represent long-range electrostatic and van der Waals interactions faithfully. This capability is evidenced by the prediction of adsorption energies with a low root mean square error of 1.1 kcal mol-1 across a wide range of adsorbates. The practical applicability of our QM/MM model is further illustrated through the study of glucose isomerization and epimerization reactions catalyzed by two structurally distinct Zr-MOF catalysts, UiO-66 and MOF-808. Our QM/MM calculations closely align with experimental activation energies. Importantly, the parameter set introduced here is compatible with the widely used universal force field (UFF). Moreover, we thoroughly explore how the size of the cluster model and the choice of density functional theory (DFT) methodologies influence the simulation outcomes. This work provides an accurate and computationally efficient framework for modeling complex catalytic reactions within Zr-MOFs, contributing valuable insights into their mechanistic behaviors and facilitating further advancements in this dynamic area of research.

Structure-Energy Relationship Prediction of the HZSM-5 Zeolite with Different Acid Site Distributions by the Neural Network Model

Zeolites are a very important family of catalysts. The catalytic activity of zeolites depends on the distribution of acid sites, which has been extensively studied. However, the relationship between the acid site distribution and catalytic efficiency remains unestablished. An onerous computational burden can be imposed when static calculations are applied to analyze the relationship between a catalyst structure and its energy. To resolve this issue, the current work uses neural network (NN) models to evaluate the relationship. By taking the typical HZSM-5 zeolite as an example, we applied the provided atomic coordinates to predict the energy. The network performances of the artificial neural network (ANN) and high-dimensional neural network (HDNN) are compared using the trained results from a dataset containing the identical number of acid sites. Furthermore, the importance of the feature is examined with the aid of a random forest model to identify the pivotal variables influencing the energy. In addition, the HDNN is employed to forecast the energy of an HZSM-5 system with varying numbers of acid sites. This study emphasizes that the energy of zeolites can be rapidly and accurately predicted through the NN, which can assist our understanding of the relationship between the structure and properties, thereby providing more accurate and efficient methods for the application of zeolite materials.

Integrating Chemical Information into Reinforcement Learning for Enhanced Molecular Geometry Optimization

Geometry optimization is a crucial step in computational chemistry, and the efficiency of optimization algorithms plays a pivotal role in reducing computational costs. In this study, we introduce a novel reinforcement-learning-based optimizer that surpasses traditional methods in terms of efficiency. What sets our model apart is its ability to incorporate chemical information into the optimization process. By exploring different state representations that integrate gradients, displacements, primitive type labels, and additional chemical information from the SchNet model, our reinforcement learning optimizer achieves exceptional results. It demonstrates an average reduction of about 50% or more in optimization steps compared to the conventional optimization algorithms that we examined when dealing with challenging initial geometries. Moreover, the reinforcement learning optimizer exhibits promising transferability across various levels of theory, emphasizing its versatility and potential for enhancing molecular geometry optimization. This research highlights the significance of leveraging reinforcement learning algorithms to harness chemical knowledge, paving the way for future advancements in computational chemistry.

In-depth analysis of the effect of catalysts on plasma technologies for treatment of various wastes

Energy security and waste management are gaining global attention. The modern world is producing a large amount of liquid and solid waste as a result of the increasing population and industrialization. A circular economy encourages the conversion of waste to energy and other value-added products. Waste processing requires a sustainable route for a healthy society and clean environment. One of the emerging solutions for waste treatment is plasma technology. It converts waste into syngas, oil, and char/slag depending on the thermal/non-thermal processes. Most of all the types of carbonaceous wastes can be treated by plasma processes. The addition of a catalyst to the plasma process is a developing field as plasma processes are energy intensive. This paper covers the detailed concept of plasma and catalysis. It comprises various types of plasma (non-thermal and thermal) and catalysts (zeolites, oxides, and salts) which have been used for waste treatment. Catalyst addition improves gas yield and hydrogen selectivity at moderate temperatures. Depending on the properties of the catalyst and type of plasma, comprehensive points are listed for the selection of the right catalyst for a plasma process. This review offers an in-depth analysis of the research in the field of waste-to-energy using plasma-catalytic processes.

Molecular Views on Mechanisms of Brønsted Acid-Catalyzed Reactions in Zeolites

The Brønsted acidity of proton-exchanged zeolites has historically led to the most impactful applications of these materials in heterogeneous catalysis, mainly in the fields of transformations of hydrocarbons and oxygenates. Unravelling the mechanisms at the atomic scale of these transformations has been the object of tremendous efforts in the last decades. Such investigations have extended our fundamental knowledge about the respective roles of acidity and confinement in the catalytic properties of proton exchanged zeolites. The emerging concepts are of general relevance at the crossroad of heterogeneous catalysis and molecular chemistry. In the present review, emphasis is given to molecular views on the mechanism of generic transformations catalyzed by Brønsted acid sites of zeolites, combining the information gained from advanced kinetic analysis, in situ, and operando spectroscopies, and quantum chemistry calculations. After reviewing the current knowledge on the nature of the Brønsted acid sites themselves, and the key parameters in catalysis by zeolites, a focus is made on reactions undergone by alkenes, alkanes, aromatic molecules, alcohols, and polyhydroxy molecules. Elementary events of C-C, C-H, and C-O bond breaking and formation are at the core of these reactions. Outlooks are given to take up the future challenges in the field, aiming at getting ever more accurate views on these mechanisms, and as the ultimate goal, to provide rational tools for the design of improved zeolite-based Brønsted acid catalysts.