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. 

The discovery and optimization of porous materials, particularly metal–organic frameworks (MOFs), are critical for advancing a range of applications, including gas storage, separation, catalysis, and energy technologies. Traditional molecular modeling methods such as Monte Carlo simulations, molecular dynamics (MD), and quantum based method such as density functional theory (DFT), has long provided valuable insights into material behavior but is often limited by high computational costs, scalability challenges, and the vast complexity of material design spaces. Machine learning has addressed some of these limitations but often requires extensive datasets, which introduce new challenges in computational efficiency. Active learning (AL) has emerged as a promising approach, offering a data-efficient framework to address these limitations. AL minimizes computational demands while maintaining high predictive accuracy by iteratively refining surrogate models and prioritizing the acquisition of the most informative data points. This review presents AL across the major tasks in MOF research: single- and multicomponent adsorption (including universal, cross-adsorbate surrogates built via alchemical-to-real transfer), diffusion and transport, electronic-structure/property prediction, experiment-in-the-loop optimization, and the training of machine-learned interatomic potentials (MLIPs). Case studies show AL recovering full isotherms and mixture landscapes with a fraction of grand canonical Monte Carlo labels, cutting MD trajectories for diffusivity, curating balanced sets for band gaps and adsorption targets, and enabling near-DFT MLIPs that capture rare events and phase changes through enhanced-sampling or uncertainty-biased data acquisition. Looking forward, we outline a path to end-to-end discovery that couples AL with generative MOF models, graph neural networks, foundational MLIPs, and that integrates experimental feedback. Together, these advances move AL beyond label efficiency toward reliable, scalable discovery workflows for gas storage, separations, catalysis, and stability screening in MOFs. 

Electrostatic configurations─the spatial arrangement of charged sites within an adsorbent─can profoundly influence the adsorbent’s interaction with water and the resulting cluster formation and their orientation. This design feature can serve as a tuning parameter for water vapor adsorption to achieve the desired isotherm behavior. Hence, understanding the role of electrostatic configurations in water vapor adsorption can inform many established and emerging areas concerning the water-energy nexus and water security. In this work, we apply continuous fractional component grand canonical Monte Carlo (CFC-GCMC) to perform water adsorption simulations in idealized cylindrical nanopores across five different charge configurations with varying pore sizes (1, 1.1, and 1.2 nm) and charge magnitudes (∼±0.39–1.17). The alternating along (AA) configuration (positive charges in the inner ring and negative charges in the outer ring while alternating in the z-direction) demonstrates higher water uptake at saturation, and water adsorption starts at a much lower pressure than other configurations. Analysis of the water clustering pattern in AA reveals both radial and axial expansions of water clusters, which facilitates accommodation of extra water molecules. Increasing the charge magnitude shifts the type-V isotherm inflection point to lower pressure, thereby increasing the hydrophilic nature of the cylinder. Probing different energetic interactions and electrostatic potentials of the configuration suggests the unique relaxation of the water clusters in the AA patterned cylinders. Investigating the effect of charge magnitude and pore size provides more insight into their hydrophilic nature. Finally, analyzing the hydrogen bonding and adsorbed phase characteristics at saturation hints at strong ordering induced by pore confinements and electrostatic configurations compared with bulk liquid water. The simulations show that tailored charge arrangements can enhance adsorption by facilitating uptake at a lower pressure and achieving a higher water capacity at saturation. This study presents original insights into the interplay of electrostatic configuration, pore size, and charge strength in controlling water vapor adsorption within nanopores and the resulting confined water vapor structure. 

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.