Predicted Adsorption Energies Research Articles

Removal of acetaminophen from wastewater using a novel bimetallic La/Th metal-organic framework: Kinetics, thermodynamics, isotherms, and optimization through Box-Behnken design

Acetaminophen (ACT), a common drug pollutant, has been effectively removed from wastewater by a novel adsorbent called La/Th-MOF. This adsorbent is made of stacked nanorods of 2-methyl imidazole with lanthanum and thorium. La/Th-MOF, which is characterized by sophisticated techniques including SEM, XRD, and BET analysis, has a mesoporous assembly with a 1.23 nm pore size and a capacious surface area of 2226.93 m2/g, which facilitates effectual adsorption. The adsorption tests, which were impacted by factors such as pH levels, ACT concentration, and contact time, fit into a pseudo-second-order chemisorption kinetic model and with the Langmuir isotherm, suggesting homogenous monolayer adsorption. The material in question demonstrated a noteworthy maximum adsorption capability of 339.75 mg/g for ACT, indicating its probable as a feasible and economical adsorbent for the mitigation of pharmaceutical contamination in wastewater. Our results designate that pH levels have an important influence on the efficacy of ACT absorption by La/Th-MOF, with an acidic pH 5 environment being most favorable for maximal adsorption at a material dosage of 0.02 g. It was discovered that the adsorption procedure was endothermic. Using pseudo-second-order kinetic models and the Langmuir isotherm, which both fit the experimental data very well, to explain the adsorption kinetics. A chemisorption mechanism was found to be predominant throughout the process, as specified by the predicted adsorption energy of 22.62 kJ/mol. In addition, optimized the influencing parameters by using the Box-Behnken design (BBD) and response surface methodology (RSM), which improved process efficiency. La/Th-MOF, has a remarkable half-life, as demonstrated by six rounds of adsorption and desorption without a discernible decline in performance. Research endeavors aimed at elucidating the interplay between La/Th-MOF and ACT hint to several plausible points of contact that could contribute to the adsorption procedure, such as hydrogen bonding, π-π interactions, pore filling or electrostatic forces. This study, which is innovative in its use, reveals the exceptional efficacy of La/Th-MOF in wastewater purification using ACT extraction. An astounding 339.75 mg/g of optimal adsorption capability was attained at an acidic pH of 5. This highlights how the La/Th-MOF can be used in practice to treat pharmaceutical pollutants found in water sources.

Two-stage feature selection for machine learning-aided DFT-based surface reactivity study on single-atom alloys

This paper presents a feature-centric strategy for predicting adsorption energies of key CO2 reduction reaction (CO2RR) adsorbates, CO and H species, utilizing density functional theory-based calculations for eight adsorption sites and considering alloying effects of nine transition metals at single-atom concentrations. Here, we explore a class of materials consisting of a majority host metal where individual atoms of a different element are dispersed called single-atom alloys (SAA). A total of eight feature selection methods are assessed within Gradient Boosting Regression and Linear Regression models. This study proposes a practical and effective two-stage approach that narrows down the initial 86 features to subsets of 10 and 7 for CO and H adsorption energy predictions, respectively, with the arithmetic mean of valence electrons (VE-am) feature consistently emerging as highly influential, validated through permutation and Shapley additive explanations-based feature importance analyses. The models exhibit robust performance on unseen data, indicating their generalization capability. The findings emphasize VE-am as a potential key machine learning feature for CO2RR on SAA surfaces and underline the effectiveness of the feature-centric approach in understanding feature impacts in machine learning models for CO2RR on SAA systems. Additionally, while other features based on structural, electronic and elemental properties may not individually impact the model significantly, their collective contribution plays a vital role in achieving more accurate adsorption energy predictions.

Li decorated graphene like MgN4 monolayer for hydrogen storage: A first-principles approach

The rapid advancement of hydrogen storage materials possessing high storage capacity, long life-cycle, reversibility, and rapid kinetics is a trending issue. Metal decoration of a two-dimensional material is a successful method of enhancing hydrogen storage capacity. Li-decorated 2D MgN4 has been inspected as a hydrogen storage material for practical applications employing density functional theory simulations. Our findings indicate that the substrate (LiMgN4) may adsorb up to 6 molecules of H2 with a gravimetric storage capacity of 1.83 wt.%, making it a viable choice for storage medium. With an average adsorption energy of 0.21 eV per H2, hydrogen is effectively sensed by Li-augmented MgN4 monolayer. Additionally, two-sided Li-decoration is discussed with 12 H2 adsorbed on each side with a storage capacity of 6.86 wt.% with an average adsorption energy of 0.15 eV/H2. High desorption temperature confirms the effective desorption of H2 from the substrate. The Li-decorated porous MgN4 responds effectively in the adsorbate (H2) environment. The predicted adsorption energy, recovery time and desorption temperature demonstrate that LiMgN4 is an exceptional choice for energy storage devices.

Invariant Molecular Representations for Heterogeneous Catalysis.

Catalyst screening is a critical step in the discovery and development of heterogeneous catalysts, which are vital for a wide range of chemical processes. In recent years, computational catalyst screening, primarily through density functional theory (DFT), has gained significant attention as a method for identifying promising catalysts. However, the computation of adsorption energies for all likely chemical intermediates present in complex surface chemistries is computationally intensive and costly due to the expensive nature of these calculations and the intrinsic idiosyncrasies of the methods or data sets used. This study introduces a novel machine learning (ML) method to learn adsorption energies from multiple DFT functionals by using invariant molecular representations (IMRs). To do this, we first extract molecular fingerprints for the reaction intermediates and later use a Siamese-neural-network-based training strategy to learn invariant molecular representations or the IMR across all available functionals. Our Siamese network-based representations demonstrate superior performance in predicting adsorption energies compared with other molecular representations. Notably, when considering mean absolute values of adsorption energies as 0.43 eV (PBE-D3), 0.46 eV (BEEF-vdW), 0.81 eV (RPBE), and 0.37 eV (scan+rVV10), our IMR method has achieved the lowest mean absolute errors (MAEs) of 0.18 0.10, 0.16, and 0.18 eV, respectively. These results emphasize the superior predictive capacity of our Siamese network-based representations. The empirical findings in this study illuminate the efficacy, robustness, and dependability of our proposed ML paradigm in predicting adsorption energies, specifically for propane dehydrogenation on a platinum catalyst surface.

Local descriptors-based machine learning model refined by cluster analysis for accurately predicting adsorption energies on bimetallic alloys

The CatBoost method, combined with cluster filtering, accurately predicts adsorption energies on metal alloys. The approach uses local chemical descriptors to understand chemisorption on metal alloys, which is essential for catalytic applications.

A prediction model for CO2/CO adsorption performance on binary alloys based on machine learning.

Despite the rapid development of computational methods, including density functional theory (DFT), predicting the performance of a catalytic material merely based on its atomic arrangements remains challenging. Although quantum mechanics-based methods can model 'real' materials with dopants, grain boundaries, and interfaces with acceptable accuracy, the high demand for computational resources no longer meets the needs of modern scientific research. On the other hand, Machine Learning (ML) method can accelerate the screening of alloy-based catalytic materials. In this study, an ML model was developed to predict the CO2 and CO adsorption affinity on single-atom doped binary alloys based on the thermochemical properties of component metals. By using a greedy algorithm, the best combination of features was determined, and the ML model was trained and verified based on a data set containing 78 alloys on which the adsorption energy values of CO2 and CO were calculated from DFT. Comparison between predicted and DFT calculated adsorption energy values suggests that the extreme gradient boosting (XGBoost) algorithm has excellent generalization performance, and the R-squared (R2) for CO2 and CO adsorption energy prediction are 0.96 and 0.91, respectively. The errors of predicted adsorption energy are 0.138 eV and 0.075 eV for CO2 and CO, respectively. This model can be expected to advance our understanding of structure-property relationships at the fundamental level and be used in large-scale screening of alloy-based catalysts.

DFT and MCDS Outcome for a Comparative Analysis of NO, NO2, SO, SO2 and SO3 Gas Adsorption onto a NaMgPO4 (033) Surface

The research purpose of this work is to examine the adsorption interaction of gaseous molecules (GMs), such as NO, NO2, SO, SO2, and SO3, with the surface of sodium magnesium phosphate NaMgPO4 (033), in a neutral medium, using two different computational methods: density functional theory (DFT) and Monte Carlo dynamic simulation (MCDS). Various quantum and dynamic descriptors, such as global and local quantum descriptors and the radial distribution function (RDF), are also evaluated and discussed. The data obtained revealed that the NO2 molecule has a small energy gap (0.363 eV) when compared to the other molecules, which means that it is highly reactive and is liable to adsorb, or stick, to the surface of NaMgPO4 (033). Furthermore, this NO2 molecule exhibits good adsorption in aqueous media, returning to the lowest global hardness value (0.1815 eV). MCDS predicted adsorption energies of −874.03, −819.94, −924.81, −876.33, and −977.71 kcal/mol for NO, NO2, SO, SO2, and SO3, respectively. These energies are negative, implying that adsorption occurs spontaneously. Thus, the side views indicated which SO, NO, and SO3 molecules are adsorbed in parallel to NaMgPO4 and the other SO2 and NO2 molecules are adsorbed horizontally. Eventually, the theoretical results reveal that the studied gaseous molecules interact strongly with NaMgPO4. The result obtained by radial distribution function (RDF) analysis for all complexes below 3.5 Å confirm that the adsorption is of the chemi1cal type.

Small-Molecule Adsorption Energy Predictions for High-Throughput Screening of Electrocatalysts.

Predicting adsorption energies of small molecules (e.g., OH, OOH, CO) on electrocatalysts involved in electrochemical reactions aids in accelerating the design and screening of electrocatalysts. Avoiding computationally expensive electronic structure calculations increases the speed of such predictions. Geometric and electronic descriptors have been reported to characterize the environment around surface active sites and predict adsorption energies. However, these descriptors cannot be used to predict adsorption energies of small molecules on various substrates, e.g., metal-oxide and nonmetal electrocatalysts. We compare the performance of these descriptors in predicting adsorption energies of small molecules on various electrocatalysts with adsorption energies calculated from density functional theory. We show that two recently developed machine learning algorithms, Crystal Graph Convolutional Neural Network (CGCNN) and Atomistic Line Graph Neural Network (ALIGNN), outperform the reported descriptors based on geometric (coordination number of the active site and its nearest neighbors) and electronic (the bond-energy-integrated orbitalwise coordination number, the electronegativity, and the number of valence electrons of the active site) properties in predicting the adsorption energies. Our results suggest that ALIGNN is almost always more accurate than CGCNN in adsorption energy predictions. The improvement ranges from 0.02 to 1.0 eV in the mean absolute errors (MAEs). We also compare the performance of CGCNN and ALIGNN algorithms in predicting the overpotentials of the oxygen evolution reaction occurring on various electrocatalysts with MAEs of 0.06 and 0.05 V, respectively.

A graph neural network model with local environment pooling for predicting adsorption energies

Adsorption energy is an important descriptor of catalytic activity in modelling heterogeneous catalysis and is used to guide novel catalyst discovery. Previously, graph neural networks (GNNs) with global pooling have been applied to predict adsorption energy on different materials. However, adsorption energy is determined largely by the atoms near the adsorbate, and thus using local pooling methods that focus on this local chemical environment should enhance catalytic predictions. This study demonstrates the use of local environment pooling instead of the global pooling in conjunction with GNNs to predict adsorption energy. Based on the neural message passing with edge updates network and DimeNet++, we achieved mean absolute errors (MAEs) of 0.096 and 0.073 eV in predicting CO and H adsorption energies, respectively, on transition metal catalyst surfaces. Notably, these values surpass the performance of previously reported state-of-the-art machine learning models that employed the labelled site crystal graph convolutional neural network.

Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.

Predicting adsorption energies and the physical properties of H, N, and O adsorbed on transition metal surfaces: A machine learning study

We present a machine learning study utilizing the Hierarchically Interacting Particle Neural Network to predict the adsorption properties of atomic H, N, and O on various single metal and bimetallic single crystal FCC surfaces. Our trained HIP-NN models directly predict, from atomic species and coordinates of the clean surface, and initial adsorption site, adsorption energies with a MAE of 0.08 eV to 0.16 eV, adsorption heights with a MAE of 0.08 Å to 0.09 Å, and a buckling of the first layer of the substrate with a MAE of 0.07 Å to 0.12 Å, illustrating that a neural network can calculate the physical properties of a surface/adsorbate system along with adsorption energy. Our MAEs for adsorption energy also compare favorably with MAEs presented by other works predicting the adsorption energies of H, N, and O. We also demonstrate that while HIP-NN can predict on these systems without explicit periodic boundary conditions, the inclusion of explicit periodic boundary conditions drastically improves the results. Our results also reveal that the buckling of the first layer of the substrate can be utilized to prune datasets, removing unstable surfaces.

Machine learning approach for screening alloy surfaces for stability in catalytic reaction conditions

A catalytic surface should be stable under reaction conditions to be effective. However, it takes significant effort to screen many surfaces for their stability, as this requires intensive quantum chemical calculations. To more efficiently estimate stability, we provide a general and data-efficient machine learning (ML) approach to accurately and efficiently predict the surface energies of metal alloy surfaces. Our ML approach introduces an element-centered fingerprint (ECFP) which was used as a vector representation for fitting models for predicting surface formation energies. The ECFP is significantly more accurate than several existing feature sets when applied to dilute alloy surfaces and is competitive with existing feature sets when applied to bulk alloy surfaces or gas-phase molecules. Models using the ECFP as input can be quite general, as we created models with good accuracy over a broad set of bimetallic surfaces including most d-block metals, even with relatively small datasets. For example, using the ECFP, we developed a kernel ridge regression ML model which is able to predict the surface energies of alloys of diverse metal combinations with a mean absolute error of 0.017 eV atom−1. Combining this model with an existing model for predicting adsorption energies, we estimated segregation trends of 596 single-atom alloys (SAAs)with and without CO adsorbed on these surfaces. As a simple test of the approach, we identify specific cases where CO does not induce segregation in these SAAs.

Ab Initio to Activity: Machine Learning-Assisted Optimization of High-Entropy Alloy Catalytic Activity

High-entropy alloys are slowly making their debut as a platform for catalyst discovery, but conventional methods, theoretical as well as experimental, may fall short of screening the vast composition space inhabited by this class of materials. New theoretical approaches are needed to gauge the catalytic activity of high-entropy alloys and optimize the alloy composition within a feasible time frame as a prerequisite for further experimental studies. Herein, we establish a workflow for simulations of catalysis on high-entropy alloy surfaces. For each step of the modeling we present our choice of method, however, we also acknowledge that alternative options are available. We apply the developed methodology to predict the net catalytic activity of any alloy composition, within the composition space spanned by Ag–Ir–Pd–Pt–Ru, for the oxygen reduction reaction. Based on first-principle calculations, a graph convolution neural network is used to predict adsorption energies of *OH and *O. Subsequently, taking competitive co-adsorption of reaction intermediates into account, we couple the net adsorption energy distribution of a high-entropy alloy surface to the expected current density. Lastly, this procedure is used in conjunction with a Bayesian optimization scheme to search for optimal alloy compositions, which yields several promising compositions. This result shows that an unbiased in silico pre-screening and discovery of catalyst candidates is viable and will help scale the otherwise insurmountable challenge of searching for high-entropy alloy catalysts. It is our hope that our computational framework, which is freely available on GitHub, will aid other research groups to efficiently identify promising high-entropy alloy catalysts.

Exploring Structure-Sensitive Relations for Small Species Adsorption Using Machine Learning.

Accurate prediction of adsorption energies on heterogeneous catalyst surfaces is crucial to predicting reactivity and screening materials. Adsorption linear scaling relations have been developed extensively but often lack accuracy and apply to one adsorbate and a single binding site type at a time. These facts undermine their ability to predict structure sensitivity and optimal catalyst structure. Using machine learning on nearly 300 density functional theory calculations, we demonstrate that generalized coordination number scaling relations hold well for oxygen- and high-valency carbon-binding species but fail for others. We reveal that the valency and the electronic coupling of a species with the surface, along with the site type and its coordination environment, are critical for small species adsorption. The model simultaneously predicts the adsorption energy and preferred site and significantly outperforms linear scalings in accuracy. It can expose the structure sensitivity of chemical reactions and enable enhanced catalyst activity via engineering particle shape and facet defects. The generality of our methodology is validated by training the model with transition metal data and transferring it to predict adsorption energies on single-atom alloys.

Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property.

The use of machine learning (ML) is exploding in materials science as a result of its high predictive performance of material properties. Tremendous trainable parameters are required to build an outperforming predictive model, which makes it impossible to retrace how the model predicts well. However, it is necessary to develop a ML model that can extract human-understandable knowledge while maintaining performance for a universal application to materials science. In this study, we developed a deep learning model that can interpret the correlation between surface electronic density of states (DOSs) of materials and their chemisorption property using the attention mechanism that provides which part of DOS is important to predict adsorption energies. The developed model constructs the well-known d-band center theory without any prior knowledge. This work shows that human-interpretable knowledge can be extracted from complex ML models.

N/O→B dative bonds supplemented by N-HN/HC hydrogen bonds make BN-cages an attractive candidate for DNA-nucleobase adsorption - an MP2 prediction.

The response of B12N12-nanocages towards DNA-nucleobases (adenine, guanine, cytosine, and thymine) is investigated using MP2 and DFT (M06-2X) levels of theory with the 6-311+G** basis set. Multiple BN-cage-nucleobase structures for each nucleobase emerged depending on the number of Lewis base centers of nucleobases. The main source of stability of these complexes is the N/O→B dative bond, where the N or O atom of nucleobases donates the lone-pair electron to one of the boron atoms of the nanocage. Nitrogen atoms of the BN-cage, adjacent to the B-site forming dative bond, act as a proton acceptor to form multiple (N-HN and N-HC) hydrogen bonds, where proton-donors NH and CH are part of nucleobases. MP2/6-311+G** adsorption energies are -43.1, -43.4 and -45.3 kcal mol-1 (B12N12-adenine), -37.1, -41.9 and -43.3 kcal mol-1 (B12N12-guanine), -41.3 and -43.4 (B12N12-cytosine), and -29.3 and -31.3 (B12N12-thymine). Similar adsorption energies were recorded for larger BN-fullerenes-nucleobases, namely B16N16 and B24N24. Changes in adsorption energies and structures of these nano-bio-hybrid materials in aqueous media are also discussed. Computationally cost-effective MP2 single point calculations at the M06-2X optimized geometries were found to be reliable in predicting adsorption energies. The effect of the BN-network and H-bonds on the adsorption process is assessed by comparing the results with simple BH3-nucleobase models. BSSE correction to the adsorption energy is not recommended.

A transferable machine-learning scheme from pure metals to alloys for predicting adsorption energies

We propose a transferable machine-learning model based on the intrinsic descriptors, which can predict the adsorption energies of single-atom alloys, AB intermetallics and high-entropy alloys , simply by training the properties of transition metals.

Arsenic adsorption on Mn3O4 surface: As(OH)3/AsO(OH)3 oxidation mechanism

The adsorptive and oxidative properties of hausmannite (Mn3O4) are used to prevent the environmental impact of arsenic-rich tailings. Density Functional/plane-wave calculations have been performed to investigate the oxidation mechanism of arsenite to arsenate species on (001) hausmannite surfaces. The most stable cleavage plane is the (001) exposing Mn2+, Mn3+, and O2– ions in an asymmetric way. The arsenite, As(OH)3, adsorbs preferentially on Mn2+ in a monodentate-mononuclear form with a predicted adsorption energy of −34.2 kcal mol−1. The adsorption on Mn3+ adsorption sites is expected to be at least 6 kcal mol−1 higher in energy. The H2AsO4- species predominant in the environmental pH (pH = 4–8) prefer to adsorb on the Mn2+ adsorption sites in a bidentate binuclear mode with a predicted adsorption energy of –4.6 kcal mol−1, and the adsorption on Mn3+ is at least 4 kcal mol−1 higher in energy. The energy barrier for the As3+/As5+ oxidation on the Mn2+ adsorption sites is estimated to be at least 28 kcal mol−1 higher in energy than on the Mn3+ adsorption sites. Water plays a key role in the chemical reactivity of Mn3O4, promoting the oxidation of arsenite into arsenate through Mn(III)/Mn(II) reduction.

Machine Learning-Driven High-Throughput Screening of Alloy-Based Catalysts for Selective CO2 Hydrogenation to Methanol

The revolutionary development of machine learning and data science and exploration of its application in material science are huge achievements of the scientific community in the past decade. In this work, we have reported an efficient approach of machine learning-aided high-throughput screening for finding selective earth-abundant high-entropy alloy-based catalysts for CO2 to methanol formation using a machine learning algorithm and microstructure model. For this, we have chosen earth-abundant Cu, Co, Ni, Zn, and Mg metals to form various alloy-based compositions (bimetallic, trimetallic, tetrametallic, and high-entropy alloys) for selective CO2 reduction reaction toward CH3OH. Since there are several possible surface microstructures for different alloys, we have used machine learning along with DFT calculations for high-throughput screening of the catalysts. In this study, the stability of various 8-atom fcc periodic (111) surface unit cells has been calculated using the atomic-size difference factor (δ) as well as the ratio taken from Gibbs free energy of mixing (Ω). Thinking about the simplicity and accuracy, microstructure models by considering the neighboring atoms of the adsorption sites and others as Cu atoms have been considered for different adsorption sites (on-top, bridge, and hollow-hcp). Moreover, the adsorption energies of the *H, *O, *CO, *HCO, *H2CO, and *H3CO intermediates have been predicted using the best fitted algorithm of the training set. The predicted adsorption energies have been screened based on the pure Cu adsorption energy. Furthermore, the screened catalysts have been correlated among different adsorption site microstructures. At the end, we were able to find seven active catalysts, among which two catalysts are CuCoNiZn-based tetrametallic, three catalysts are CuNiZn-based trimetallic, and two catalysts are CuCoZn-based trimetallic alloys. Hence, this work demonstrates not an ultimate but an efficient approach for finding new product-selective catalysts, and we expect that it can be convenient for other similar types of reactions in forthcoming days.

Learning the Use of Artificial Intelligence in Heterogeneous Catalysis

We describe the use of artificial intelligence techniques in heterogeneous catalysis. This description is intended to give readers some clues for the use of these techniques in their research or industrial processes related to hydrodesulfurization. Since the description corresponds to supervised learning, first of all, we give a brief introduction to this type of learning, emphasizing the variables X and Y that define it. For each description, there is a particular emphasis on highlighting these variables. This emphasis will help define them when one works on a new application. The descriptions that we present relate to the construction of learning machines that infer adsorption energies, surface areas, adsorption isotherms of nanoporous materials, novel catalysts, and the sulfur content after hydrodesulfurization. These learning machines can predict adsorption energies with mean absolute errors of 0.15 eV for a diverse chemical space. They predict more precise surface areas of porous materials than the BET technique and can calculate their isotherms much faster than the Monte Carlo method. These machines can also predict new catalysts by learning from the catalytic behavior of materials generated through atomic substitutions. When the machines learn from the variables associated with a hydrodesulfurization process, they can predict the sulfur content in the final product.