Machine Learning-Assisted Computational Screening of Metal-Organic Frameworks for Atmospheric Water Harvesting

Abstract

Atmospheric water harvesting by strong adsorbents is a feasible method of solving the shortage of water resources, especially for arid regions. In this study, a machine learning (ML)-assisted high-throughput computational screening is employed to calculate the capture of H2O from N2 and O2 for 6013 computation-ready, experimental metal-organic frameworks (CoRE-MOFs) and 137,953 hypothetical MOFs (hMOFs). Through the univariate analysis of MOF structure-performance relationships, Qst is shown to be a key descriptor. Moreover, three ML algorithms (random forest, gradient boosted regression trees, and neighbor component analysis (NCA)) are applied to hunt for the complicated interrelation between six descriptors and performance. After the optimizing strategy of grid search and five-fold cross-validation is performed, three ML can effectively build the predictive model for CoRE-MOFs, and the accuracy R2 of NCA can reach 0.97. In addition, based on the relative importance of the descriptors by ML, it can be quantitatively concluded that the Qst is dominant in governing the capture of H2O. Besides, the NCA model trained by 6013 CoRE-MOFs can predict the selectivity of hMOFs with a R2 of 0.86, which is more universal than other models. Finally, 10 CoRE-MOFs and 10 hMOFs with high performance are identified. The computational screening and prediction of ML could provide guidance and inspiration for the development of materials for water harvesting in the atmosphere.

Combining Machine Learning and Molecular Simulations to Unlock Gas Separation Potentials of MOF Membranes and MOF/Polymer MMMs

“…Machine learning (ML) is an excellent approach to analyzing a large amount of simulated material data since establishing structure–performance relations for MOFs can lead to the design and development of new MOF materials with better performances . In the last several years, ML algorithms have been used to study MOFs for various adsorption-based gas separations such as CO 2 capture, − H 2 O/(O 2 + N 2 ), H 2 S/CH 4 , propane/propylene, and Xe/Kr separations. On the other hand, ML has been used to study MOF membranes in a very limited number of studies due to the difficulty of generating gas permeability data using computationally demanding MD simulations.…”

Metal–Organic Frameworks for Water Harvesting and Concurrent Carbon Capture: A Review for Hygroscopic Materials

“…There have been considerable reports on ML-assisted MOF screening for CH 4 /H 2 storage, [154][155][156][157] CO 2 /thiol capture, [158][159][160][161] and gas separation [162,163] and sensing. [164] However, the prediction of MOF water stability is relatively underexplored because water stability and water uptake capacity need to be simultaneously catered though they require different models.…”

“…On the other side, the Qiao group reported the ML-assisted screening of MOFs to evaluate their water uptake. [160] The studies were based on the 2017 version of 6013 CoRE-MOFs collected by Chung et al [165] and a large crystallographic dataset of 137 953 hMOFs designed by Wilmer et al [166] Five structural descriptors were selected, including largest cavity diameter (LCD), porelimiting diameter (PLD), volumetric surface area (VSA), void fraction (ϕ), and density (𝜌) with one energy descriptor, heat of adsorption (Q st ). These descriptors have been proven accurate in the ML-assisted prediction of other applications (CH 4 storage, etc.).…”

Sorption‐Based Atmospheric Water Harvesting: Materials, Components, Systems, and Applications

“…Computer screening and simulations based on machine learning could provide guidance and inspiration for the development of materials, especially synthetic sorbents, to collect water in the atmosphere. [ 80 ] Although there are many opportunities to expand this emerging and exciting field both in terms of material and device development, yet the current sorption capacity of organic frameworks is usually within that of the traditional sorbent composites range (as it can be seen in Table 2). They are also more expensive compared to traditional composites.…”