Search for: All records

Abstract The application of machine learning (ML) techniques in materials science has revolutionized the pace and scope of materials research and design. In the case of metal–organic frameworks (MOFs), a promising class of materials due to their tunable properties and versatile applications in gas adsorption and separation, ML has helped survey the vast material space. This study explores the integration of reinforcement learning (RL), specifically Q‐learning, within an active learning (AL) context, combined with Gaussian processes (GPs) for predictive modeling of adsorption in MOFs. We demonstrate the effectiveness of the RL‐driven framework in guiding the selection of training data points and optimizing predictive model performance for methane and carbon dioxide adsorption, using two different reward metrics. Our results highlight the integration of RL as an AL method for adsorption predictions in MFs, and how it compares to a previously implemented AL scheme. 

Active learning facilitated adsorption predictions in porous materials by incorporating “alchemical” molecules, fugacity, and material features (PC1, PC2) using Gaussian process regression. 

You will likely have heard of absorption before, but have you heard of adsorption? At the University of Notre Dame in Indiana, USA, Dr Yamil Colón is a chemical and biomolecular engineer studying this important chemical process. His work could help make huge breakthroughs in healthcare, climate change, environment and water scarcity research. 

In recent decades, metal–organic frameworks (MOFs) have gained recognition for their potential in multicomponent gas separations. Though molecular simulations have revealed structure–property relationships of MOF–adsorbate systems, they can be computationally expensive and there is a need for surrogate models that can predict the adsorption data faster. In this work, an active learning (AL) protocol is introduced that can predict multicomponent gas adsorption in a MOF for a range of thermodynamic conditions. This methodology is applied to build a model for the adsorption of three different gas mixtures (CO2–CH4, Xe–Kr, and H2S–CO2) in the MOF Cu-BTC. A Gaussian process regression (GPR) model is used to fit the data as well to leverage its predicted uncertainty to drive the learning. The training data is generated using grand-canonical Monte Carlo (GCMC) simulations as points are iteratively added to the model to minimize the predicted uncertainty. Also, a criteria which captures the perceived performance of the GPs is introduced to terminate the AL process when the perceived accuracy threshold is met. The three systems are tested for a pressure–mole fraction (P–X), and a pressure–mole fraction–temperature (P–X–T) feature space. It is demonstrated that AL one only needs a fraction of the data from simulations to build a reliable surrogate model for predicting mixture adsorption. Further, the final GP fit from AL outperforms ideal adsorbed solution theory predictions. 

High-throughput molecular simulations and machine learning (ML) have been implemented to adequately screen a large number of metal−organic frameworks (MOFs) for applications involving adsorption. Grand canonical Monte Carlo (GCMC) simulations have proven effective in calculating the adsorption capacity at given pressures and temperatures, but they can require expensive computational resources. While they can be resource-efficient, ML models can require large datasets, creating a need for algorithms that can efficiently characterize adsorption; active learning (AL) can play a very important role in this regard. In this work, we make use of Gaussian process regression (GPR) to model pure component adsorption of nitrogen at 77 K from 10−5 to 1 bar, methane at 298 K from 10 −5 to 100 bar, carbon dioxide at 298 K from 10−5 to 100 bar, and hydrogen at 77 K from 10−5 to 100 bar on PCN-61, MgMOF-74, DUT-32, DUT-49, MOF-177, NU-800, UiO-66, ZIF-8, IRMOF-1, IRMOF-10, and IRMOF-16. The GPR model requires an initial training of the model with an initial dataset, the prior one, and, in this study of evaluating AL, we make use of three different prior selection schemes. Each prior scheme is updated with a sampling point resulting from the GP model uncertainties. This protocol continues until a maximum GPR relative error of 2% is attained. We make a recommendation on the best prior selection scheme for the total 44 adsorbate−adsorbent pairs primarily making use of the mean absolute error and the total amount of points required for convergence of the model. To further evaluate the AL framework, we apply the BET consistency criteria on the simulated and GP nitrogen isotherms and compare the resulting surface areas. 

Metal–organic frameworks (MOFs) are promising materials with various applications, and machine learning (ML) techniques can enable their design and understanding of structure–property relationships. In this paper, we use machine learning (ML) to cluster the MOFs using two different approaches. For the first set of clusters, we decompose the data using the textural properties and cluster the resulting components. We separately cluster the MOF space with respect to their topology. The feature data from each of the clusters were then fed into separate neural networks (NNs) for direct learning on an adsorption task (methane or hydrogen). The resulting NNs were then used in transfer learning (TL) where only the last NN layer was retrained. The results show significant differences in TL performance based on which cluster is chosen for direct learning. We find TL performance depends on the Euclidean distance in the decomposed feature space between the clusters involved in the direct and TL. Similar results were found when TL was performed simultaneously across both types of clusters and adsorption tasks. We note that methane adsorption was a better source task than hydrogen adsorption. Overall, the approach was able to identify MOFs with the most transferable information, leading to valuable insights and a more comprehensive understanding of the MOF landscape. This highlights the method's potential to generate a deeper understanding of complex systems and provides an opportunity for its application in alternative datasets. 

Machine learning (ML) accelerates the exploration of material properties and their links to the structure of the underlying molecules. In previous work [Shi et al. ACS Applied Materials & Interfaces 2022, 14, 37161−37169.], ML models were applied to predict the adhesive free energy of polymer–surface interactions with high accuracy from the knowledge of the sequence data, demonstrating successes in inverse-design of polymer sequence for known surface compositions. While the method was shown to be successful in designing polymers for a known surface, extensive data sets were needed for each specific surface in order to train the surrogate models. Ideally, one should be able to infer information about similar surfaces without having to regenerate a full complement of adhesion data for each new case. In the current work, we demonstrate a transfer learning (TL) technique using a deep neural network to improve the accuracy of ML models trained on small data sets by pretraining on a larger database from a related system and fine-tuning the weights of all layers with a small amount of additional data. The shared knowledge from the pretrained model facilitates the prediction accuracy significantly on small data sets. We also explore the limits of database size on accuracy and the optimal tuning of network architecture and parameters for our learning tasks. While applied to a relatively simple coarse-grained (CG) polymer model, the general lessons of this study apply to detailed modeling studies and the broader problems of inverse materials design.