A generalized van der Waals model for light gas adsorption prediction in IRMOFs
A generalized van der Waals model for predicting the adsorption isotherms in IRMOFs by defining different attractive regions.
Kong, Lingli↗
SEARCH · Engineering Papers
Results for “adsorption predictions”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Predicting Adsorption Properties of Catalytic Descriptors on Bimetallic Nanoalloys with Site-Specific Precision
Bimetallic nanoparticles present a vastly tunable structural and compositional design space rendering them promising materials for catalytic and energy applications. Yet it remains an enduring challenge to efficiently screen candidate alloys with atomic level specificity while explicitly accounting for their inherent stabilities under reaction conditions. Herein, by leveraging correlations between binding energies of metal adsorption sites and metal–adsorbate complexes, we predict adsorption energies of typical catalytic descriptors (OH*, CH 3 *, CH*, and CO*) on bimetallic alloys with site-specific resolution. We demonstrate that our approach predicts adsorption energies on top and bridge sites of bimetallic nanoparticles having generic morphologies and chemical environments with errors between 0.09 and 0.18 eV. By forging a link between the inherent stability of an alloy and the adsorption properties of catalytic descriptors, we can now identify active site motifs in nanoalloys that possess targeted catalytic descriptor values while being thermodynamically stable under working conditions.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
ZeoNet: 3D convolutional neural networks for predicting adsorption in nanoporous zeolites
Zeolites are one of the most widely used materials in the chemical industry due to their nanometer-sized pores that can adsorb and react upon molecules selectively. With hundreds of known framework topologies and hundreds of thousands of computationally predicted structures, the ability to rapidly predict zeolite performance allows researchers to prioritize their efforts on the most promising structures for a given application. Although the accuracy of forcefield-based atomistic simulations has advanced significantly in the past two decades, these simulations can be computationally expensive, especially for long-chain, complex molecules. Here, we present ZeoNet, a representation learning framework using convolutional neural networks (ConvNets) and 3D volumetric representations for predicting adsorption in zeolites. ZeoNet was trained on the task of predicting Henry's constants for adsorption, k H , of n-octadecane in more than 330 000 known and predicted zeolite materials. Employing a 3D grid based on the distances to solvent-accessible surfaces, a volumetric representation that can be generated efficiently, the best-performing ZeoNet achieved a correlation coefficient r 2 = 0.977 and a mean-squared error MSE = 3.8 in ln k H , which corresponds to an error of 9.3 kJ mol -1 in adsorption free energy. In comparison, a model based on hand-designed geometric features has values of r 2 = 0.783 and MSE = 35.7. ZeoNet is also relatively efficient and can process ≈8 structures per second on an Nvidia RTX 2080TI GPU, orders of magnitude faster than forcefield-based simulations. A systematic analysis was conducted to investigate how the choice of ConvNet architectures, the linear dimension (L) and spatial resolution (Δd) of the distance grids, batch size, optimizer, and learning rate impact the model performance. We found that ConvNets based on the ResNet architecture offer the best tradeoff between expressiveness and efficiency. The performance for all models reaches a plateau at L = 30–45 Å and depends less sensitively on grid resolution, with a small benefit around Δd = 0.30–0.45 Å. Finally, saliency maps were visualized to identify which regions of the materials contributed the most to model predictions. It was found, interestingly, that the predictions are driven primarily by the accessible pore volume rather than the region occupied by the framework atoms.
36 MATERIALS SCIENCE↗
Machine learning using host/guest energy histograms to predict adsorption in metal–organic frameworks: Application to short alkanes and Xe/Kr mixtures
A machine learning (ML) methodology that uses a histogram of interaction energies has been applied to predict gas adsorption in metal–organic frameworks (MOFs) using results from atomistic grand canonical Monte Carlo (GCMC) simulations as training and test data. In this work, the method is first extended to binary mixtures of spherical species, in particular, Xe and Kr. In addition, it is shown that single-component adsorption of ethane and propane can be predicted in good agreement with GCMC simulation using a histogram of the adsorption energies felt by a methyl probe in conjunction with the random forest ML method. Here, the results for propane can be improved by including a small number of MOF textural properties as descriptors. We also discuss the most significant features, which provides physical insight into the most beneficial adsorption energy sites for a given application.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
A Transferable Force Field for Predicting Adsorption and Diffusion of Water in Cationic Zeolites with Coupled Cluster Accuracy
We present a transferable force field for water in proton-exchanged, alkali (Li, Na, K, Rb, and Cs) metal-exchanged, and alkaline-earth (Mg, Ca, Sr, and Ba) metal-exchanged zeolites. The fitting methodology is based on adsorbate–adsorbent interaction energies obtained from periodic density functional theory calculations and corrected using the coupled-cluster method applied to small model clusters. To ensure an accurate prediction of both adsorption and diffusion properties of water, sets of configurations that sample both adsorption sites and intracrystalline hopping transition states were used in the fitting. The quality of the force field is assessed for a wide range of zeolites with different topologies and chemical compositions, demonstrating good agreement between theoretical predictions and experimental measurements of water adsorption and diffusion.
Adsorption↗
Two-Dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials
A major obstacle for machine learning (ML) in chemical science is the lack of physically informed feature representations that provide both accurate prediction and easy interpretability of the ML model. In this work, we describe adsorption systems using novel two-dimensional energy histogram (2D-EH) features, which are obtained from the probe-adsorbent energies and energy gradients at grid points located throughout the adsorbent. The 2D-EH features encode both energetic and structural information of the material and lead to highly accurate ML models (coefficient of determination R2 ~ 0.94–0.99) for predicting single-component adsorption capacity in metal–organic frameworks (MOFs). Here, we consider the adsorption of spherical molecules (Kr and Xe), linear alkanes with a wide range of aspect ratios (ethane, propane, n-butane, and n-hexane), and a branched alkane (2,2-dimethylbutane) over a wide range of temperatures and pressures. The interpretable 2D-EH features enable the ML model to learn the basic physics of adsorption in pores from the training data. We show that these MOF-data-trained ML models are transferrable to different families of amorphous nanoporous materials. We also identify several adsorption systems where capillary condensation occurs, and ML predictions are more challenging. Nevertheless, our 2D-EH features still outperform structural features including those derived from persistent homology. The novel 2D-EH features may help accelerate the discovery and design of advanced nanoporous materials using ML for gas storage and separation in the future.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
How Useful Are Common Simulants of Chemical Warfare Agents at Predicting Adsorption Behavior?
We report that nanoporous materials such as metal–organic frameworks (MOFs) have attractive properties for selective capture of chemical warfare agents (CWAs). For obvious reasons, most research on adsorption of CWAs is performed with simulant molecules rather than real agents. This paper examines how effectively common CWA simulants mimic the adsorption properties of sarin and soman. To this end, we perform molecular simulations in the dilute adsorption limit for four simulants [dimethyl methylphosphonate (DMMP), diethyl chlorophosphate (DCP), diisopropyl fluorophosphate, and dimethyl p-nitrophenyl phosphate (DMNP)] and sarin and soman in a set of 2969 MOFs with experimentally known crystal structures. To establish the robustness of the conclusions with respect to the force field used in these simulations, each system was examined with two independent force fields, a “generic” force field and a density functional theory (DFT)-derived force field we established based on extensive dispersion-corrected DFT calculations of adsorption in the well-known MOF UiO-66. Our results show that when judging the performance of adsorbents using the heat of adsorption, DCP and DMMP are the best simulants for the adsorption of sarin, while DMNP is the best simulant for soman. The adsorption properties of DCP or DMMP show a strong correlation with sarin over a range of MOFs, but the correlation between DMNP and soman is considerably weaker. Finally, comparisons of results with both force fields indicate that our main conclusions are robust with respect to the force field used to define adsorbate–MOF interactions.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Prediction of mixed-gas adsorption equilibria from pure component adsorption isotherms
Not provided.
Engineering↗
Rapid Prediction of Adsorption Isotherms of a Diverse Range of Molecules in Hyper-Cross-Linked Polymers
Hyper-cross-linked polymers (HCPs) are materials with permanent porosity that have potential applications in adsorption-based chemical separations. We use molecular simulations to predict the largest set of adsorption isotherms available to date for HCPs. Specifically, we predict room-temperature isotherms for 24 distinct molecules in 9 different HCPs that vary in both the monomer composition and cross-link density. This information allows us to develop efficient approximate models that predict adsorption isotherms in HCPs based only on the Henry’s constant for adsorption, textural information about the HCP, and bulk phase properties of the adsorbing molecule. This approximate approach will be useful in considering the adsorption of diverse groups of molecules in HCPs in the future. Our data also enables us to describe the selectivity of adsorption for the 276 binary mixtures that can be formed from the 24 molecules we simulated. Furthermore, this information greatly expands the information that is available about adsorption selectivity in HCPs.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Comparative Study on the Machine Learning-Based Prediction of Adsorption Energies for Ring and Chain Species on Metal Catalyst Surfaces
Computation of adsorption and transition state energies for a large number of surface intermediates for numerous active site models pose significant computational overhead in computational screening of catalysts. Machine learning (ML) techniques can be used to predict part of these energies. To predict the energies, ML models need to be fed appropriate metal and species descriptors. For complex surface chemistries, the structures of the intermediate species can vary greatly. In this paper, working with the hydrodeoxygenation of succinic acid on six different metal surfaces, we have studied the effect of linear and non-linear ML models used along with pen-and-paper based species descriptors and two categories of metal descriptors on two different categories of intermediate species: chain and ring. More specifically, our computations include the prediction of chain species when trained on only chain species and also when trained on both chain and ring species. Similar computations were performed for predictions of ring species. In each case, results of linear ML models were compared with kernel based non-linear models. Our results indicate that ring species data does not improve the prediction of chain species. Similarly, chain species data does not improve the prediction of ring species. The use of non-linear ML models, however, did help to minimize the prediction errors compared to the linear models. Furthermore, the study also shows that electronic or adsorption energy based metal descriptors along with bond count based species fingerprints can achieve a mean absolute error (MAE) of less than 0.2 eV for complex chain molecules when used with an appropriate machine learning model.
Adsorption↗
Machine Learning Prediction of H Adsorption Energies on Ag Alloys
Adsorption energies on surfaces are excellent descriptors of their chemical properties, including their catalytic performance. This has prompted a significant amount of work towards efficiently predicting adsorption energies without performing expensive quantum chemical calculations, based on semi-empirical or data scientific models. Here, we develop machine learning models to predict H adsorption energies on stepped Ag surface alloys using a database of energies obtained from first-principles electronic structure calculations based on density functional theory. Starting with a simple model and iteratively refining the features extracted from the calculations, we determine the key characteristics of successful models, and reduce the number of features required for accurate prediction of the adsorption energy. We find that nonlinear models are essential for accurate predictions. Moreover, detailed comparison of model predictions and calculations reveal a counterintuitive "selfpassivation" induced by some alloying elements, as well as unexpected discontinuous electronic structure effects. These findings are rationalized using tight-binding model hamiltonians and by analyzing the electronic density of states. Lastly, we show that we can estimate the reliability of a particular prediction, mitigating the effects of errors in the small fraction of cases where these errors are significant.
36 MATERIALS SCIENCE↗
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.
36 MATERIALS SCIENCE↗
Machine learned features from density of states for accurate adsorption energy prediction
Materials databases generated by high-throughput computational screening, typically using density functional theory (DFT), have become valuable resources for discovering new heterogeneous catalysts, though the computational cost associated with generating them presents a crucial roadblock. Hence there is a significant demand for developing descriptors or features, in lieu of DFT, to accurately predict catalytic properties, such as adsorption energies. Here, we demonstrate an approach to predict energies using a convolutional neural network-based machine learning model to automatically obtain key features from the electronic density of states (DOS). The model, DOSnet, is evaluated for a diverse set of adsorbates and surfaces, yielding a mean absolute error on the order of 0.1 eV. In addition, DOSnet can provide physically meaningful predictions and insights by predicting responses to external perturbations to the electronic structure without additional DFT calculations, paving the way for the accelerated discovery of materials and catalysts by exploration of the electronic space.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Comprehensive Assessment of the Accuracy of the Ideal Adsorbed Solution Theory for Predicting Binary Adsorption of Gas Mixtures in Porous Materials
Quantifying the adsorption of chemical mixtures in porous adsorbents is critical to developing these materials for useful separation applications. The ideal adsorbed solution theory (IAST) is the most widely applied mixing theory for predicting mixture adsorption using single-component adsorption data, but a perceived lack of experimental data has limited previous efforts to explore the accuracy of IAST in a systematic way. In this paper, we take advantage of a large collection of binary experimental data for gas adsorption that became available recently to tackle this issue. Specifically, we identify more than 400 examples in which binary adsorption data and single-component data are available in the same publication and apply IAST to all these examples. This analysis includes experimental data from 63 gas mixtures of 37 different molecular species and 174 different adsorbents. In addition to being the most systematic evaluation to date of the accuracy of IAST for gas adsorption, these data will be valuable for future efforts to test or develop mixing theories that improve upon IAST.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Optimizing Polymer-Grafted Amidoxime-based Adsorbents for Uranium Uptake from Seawater
This Final Report for Project 14-6789: “Optimizing Polymer- Grafted Amidoxime-based Adsorbents for Uranium Uptake from Seawater” consists of three independent parts focused on (i) polymer design optimization, (ii) effect of environmental factors on uranium adsorption, and (iii) effect of flow rate on uranium uptake. The polymer design section focuses on the study of polymer graft-chain conformation through neutron reflectometry and the influence of conformation on adsorbent performance. The environmental effects section was divided into four subcategories: (1) investigating the impact of aqueous ions on uranium adsorption and the development of an object oriented modeling framework for analysis of aqueous adsorption modeling; (2) analyzing and predicting adsorption capacities as a function of temperature; (3) developing a multi-scale paradigm by coupling aqueous adsorption modeling with molecular level models to predict competitive adsorption between vanadium and uranium at various pH values; (4) investigating the effect of competing adsorbates on uranium adsorption capacity and the possibility of uranium recovery from desalination brine reject. The final section is concerned with determining the effect of current velocity on uranium uptake by developing an understanding of the relationship between mass transfer kinetics and flow rate.
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning
Computational catalyst screening has the potential to significantly accelerate heterogeneous catalyst discovery. Typically, this involves developing microkinetic reactor models that are based on parameters obtained from density functional theory and transition-state theory. To reduce the large computational cost involved in computing various adsorption and transition-state energies of all possible surface states on a large number of catalyst models, linear scaling relations for surface intermediates and transition states have been developed that only depend on a few, typically one or two descriptors, such as the carbon atom adsorption energy. As a result, only the descriptor values have to be computed for various active site models to generate volcano curves in activity or selectivity. Unfortunately, for more complex chemistries the predictability of linear scaling relations is unknown. Also, the selection of descriptors is essentially a trial and error process. Here, using a database of adsorption energies of the surface species involved in the decarboxylation and decarbonylation of propionic acid over eight monometalic transition-metal catalyst surfaces (Ni, Pt, Pd, Ru, Rh, Re, Cu, Ag), we tested if nonlinear machine learning (ML) models can outperform the linear scaling relations in prediction accuracy when predicting the adsorption energy for various species on a metal surface based on data from the rest of the metal surfaces. We found linear scaling relations to hold well for predictions across metals with a mean-absolute error of 0.12 eV, and ML methods being unable to outperform linear scaling relations when the training dataset contains a complete set of energies for all of the species on various metal surfaces. Only when the training dataset is incomplete, namely, contains a random subset of species’ energies for each metal, a currently unlikely scenario for catalyst screening, do kernel-based ML models significantly outperform linear scaling relations. We also found that simple coordinate-free species descriptors, such as bond counts, achieve as good results as sophisticated coordinate-based descriptors. Finally, we propose an approach for automatic discovery of appropriate metal descriptors using principal component analysis.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces
Historically, surface complexation model (SCM) constants and distribution coefficients (K d ) have been employed to quantify mineral-based retardation effects controlling the fate of metals in subsurface geologic systems. Our recent SCM development workflow, based on the Lawrence Livermore National Laboratory Surface Complexation/Ion Exchange (L-SCIE) database, illustrated a community FAIR data approach to SCM development by predicting uranium(VI)-quartz adsorption for a large number of literature-mined data. Here, we present an alternative hybrid machine learning (ML) approach that shows promise in achieving equivalent high-quality predictions compared to traditional surface complexation models. At its core, the hybrid random forest (RF) ML approach is motivated by the proliferation of incongruent SCMs in the literature that limit their applicability in reactive transport models. Our hybrid ML approach implements PHREEQC-based aqueous speciation calculations; values from these simulations are automatically used as input features for a random forest (RF) algorithm to quantify adsorption and avoid SCM modeling constraints entirely. Named the LLNL Speciation Updated Random Forest (L-SURF) model, this hybrid approach is shown to have applicability to U(VI) sorption cases driven by both ion-exchange and surface complexation, as is shown for quartz and montmorillonite cases. The approach can be applied to reactive transport modeling and may provide an alternative to the costly development of self-consistent SCM reaction databases.
38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
Machine Learning Interatomic Potentials for Modeling Framework Flexibility and Water Uptake in NbOFFIVE-1-Ni Metal–Organic Framework
Metal–organic frameworks (MOFs), with their distinctive porous structures and tunable chemical properties, have shown immense promise in the separation and storage of gases. Currently, the accurate simulation of their adsorptive properties remains challenging, especially for systems where the molecules fit very tightly into the pores. Traditional simulation methods often approximate the frameworks as rigid and do not account for the framework flexibility seen in materials such as NbOFFIVE-1-Ni. First-principles molecular dynamics (FPMD) simulations offer the desired accuracy in modeling this flexibility but are limited by their extensive computational demands, rendering them impractical for long simulations. Conversely, classical force field-based simulations offer computational efficiency but lack the necessary accuracy. Here, to break this accuracy-efficiency trade-off, we have developed machine learning interatomic potentials trained on energies and forces from FPMD to model the framework flexibility of NbOFFIVE-1-Ni in the presence of water over nanosecond time scales. Furthermore, by integrating MLIP-driven molecular dynamics (MLIP-MD) with grand canonical Monte Carlo (GCMC) simulations, we further incorporated framework flexibility into adsorption predictions, yielding water adsorption isotherms that better align with experimental data compared to those of conventional GCMC simulations. These advances offer new opportunities for the design and optimization of MOFs in gas storage and separation applications.
adsorption↗