Application of machine learning in adsorption energy storage using metal organic frameworks: A review

Journal of Energy Storage, Journal Year: 2025, Volume and Issue: 111, P. 115363 - 115363

Published: Jan. 13, 2025

Language: Английский

---

Machine learning for the advancement of membrane science and technology: A critical review

Journal of Membrane Science, Journal Year: 2024, Volume and Issue: 713, P. 123256 - 123256

Published: Sept. 3, 2024

Machine learning (ML) has been rapidly transforming the landscape of natural sciences and potential to revolutionize process data analysis hypothesis formulation as well expand scientific knowledge. ML particularly instrumental in advancement cheminformatics materials science, including membrane technology. In this review, we analyze current state-of-the-art membrane-related applications from perspectives. We first discuss foundations different algorithms design choices. Then, traditional deep methods, application examples literature, are reported. also importance both molecular membrane-system featurization. Moreover, follow up on discussion with science detail literature using data-driven methods property prediction fabrication. Various fields discussed, such reverse osmosis, gas separation, nanofiltration. differentiate between downstream predictive tasks generative design. Additionally, formulate best practices minimum requirements for reporting reproducible studies field membranes. This is systematic comprehensive review science.

Language: Английский

---

Machine Learning in Computational Design and Optimization of Disordered Nanoporous Materials

Materials, Journal Year: 2025, Volume and Issue: 18(3), P. 534 - 534

Published: Jan. 24, 2025

This review analyzes the current practices in data-driven characterization, design and optimization of disordered nanoporous materials with pore sizes ranging from angstroms (active carbon polymer membranes for gas separation) to tens nm (aerogels). While machine learning (ML)-based prediction screening crystalline, ordered porous are conducted frequently, porosity receive much less attention, although ML is expected excel field, which rich ill-posed problems, non-linear correlations a large volume experimental results. For micro- mesoporous solids carbons, silica, aerogels, etc.), obstacles mostly related navigation available data transferrable easily interpreted features. The majority published efforts based on obtained same work, datasets often very small. Even limited data, helps discover non-evident serves material production optimization. development comprehensive databases low-level structural sorption characteristics, as well automated synthesis/characterization protocols, seen direction immediate future. paper written language readable by chemist unfamiliar science specifics.

Language: Английский

---

The role of voronoi catalytic porous foam in reactive flow for hydrogen production through steam methane reforming (SMR): A pore-scale investigation

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Language: Английский

---

Experimental performance analysis of methanol adsorption in granular activated carbon packed bed through design of a double pipe heat exchanger with longitudinal fins

International Communications in Heat and Mass Transfer, Journal Year: 2024, Volume and Issue: 158, P. 107938 - 107938

Published: Aug. 13, 2024

Language: Английский

---

A guided review of machine learning in the design and application for pore nanoarchitectonics of carbon materials

Materials Science and Engineering R Reports, Journal Year: 2025, Volume and Issue: 165, P. 101010 - 101010

Published: May 3, 2025

Language: Английский

---

Machine Learning-Based Model for Prediction Permeability in Porous Media: Method and Application to Unconventional Reservoirs

International Petroleum Technology Conference, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

Abstract Accurately predicting permeability in porous media is crucial for various engineering fields, including petroleum engineering, geology, and environmental science. Unlike conventional reservoirs, shale reservoirs predominantly feature micro- to nano-scale pores, making prediction challenging difficult obtain through experimental methods. This research presents an innovative model based on machine learning address these challenges. By leveraging data-driven approaches, this work establishes a workflow media. The study employs hybrid CNN-BiLSTM-Attention model, incorporating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), attention mechanism predict using pore-throat parameters. dataset, generated Quartet Structure Generation Set method pore network models, consists of 600 randomly created samples. Key finding include: (1) the proposed outperforms traditional models (MLP, CNN, CNN-BiLSTM), with RMSE, MAE, R2 values 0.0076, 0.0058, 0.97, respectively; (2) most influential factors affecting are mean radius, throat porosity; (3) successfully predicts oil reservoir samples, closely matching results. offers highly efficient accurate prediction, particularly suited unconventional providing potential applications evaluation enhanced recovery strategies.

Language: Английский

---

Research Progress on Micro/Nanopore Flow Behavior

Molecules, Journal Year: 2025, Volume and Issue: 30(8), P. 1807 - 1807

Published: April 17, 2025

Fluid flow in microporous and nanoporous media exhibits unique behaviors that deviate from classical continuum predictions due to dominant surface forces at small scales. Understanding these microscale mechanisms is critical for optimizing unconventional reservoir recovery other energy applications. This review provides a comparative analysis of the existing literature, highlighting key advances experimental techniques, theoretical models, numerical simulations. We discuss how innovative micro/nanofluidic devices high-resolution imaging methods now enable direct observation confined phenomena, such as slip flow, phase transitions, non-Darcy behavior. Recent models have clarified scale-dependent regimes by distinguishing effects macroscopic Darcy flow. Likewise, advanced simulations—including molecular dynamics (MD), lattice Boltzmann (LBM), hybrid multiscale frameworks—capture complex fluid–solid interactions multiphase under realistic pressure wettability conditions. Moreover, integration artificial intelligence (e.g., data-driven modeling physics-informed neural networks) accelerating data interpretation modeling, offering improved predictive capabilities. Through this review, adsorption layers, interactions, pore heterogeneity, are examined across studies, persistent challenges identified. Despite notable progress, remain replicating true conditions, bridging fully characterizing interface dynamics. By consolidating recent progress perspectives, not only summarizes state-of-the-art but underscores remaining knowledge gaps future directions micro/nanopore research.

Language: Английский

---

Development of the CO₂ Adsorption Model on Porous Adsorbent Materials Using Machine Learning Algorithms

ACS Applied Energy Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 19, 2024

Language: Английский

---

Scaling the predictions of multiphase flow through porous media using operator learning

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 503, P. 157671 - 157671

Published: Dec. 2, 2024

Language: Английский

---