Machine learning prediction on the fractional free volume of polymer membranes

Journal of Membrane Science, Год журнала: 2022, Номер 665, С. 121131 - 121131

Опубликована: Окт. 27, 2022

Язык: Английский

---

A review on the application of molecular descriptors and machine learning in polymer design

Polymer Chemistry, Год журнала: 2023, Номер 14(29), С. 3325 - 3346

Опубликована: Янв. 1, 2023

Molecular descriptors and machine learning are useful tools for extracting structure–property relationships from large, complex polymer data, accelerating the design of novel polymers with tailored functionalities.

Язык: Английский

---

Machine‐Learning‐Accelerated Development of Efficient Mixed Protonic–Electronic Conducting Oxides as the Air Electrodes for Protonic Ceramic Cells

Advanced Materials, Год журнала: 2022, Номер 34(51)

Опубликована: Сен. 30, 2022

Currently, the development of high-performance protonic ceramic cells (PCCs) is limited by scarcity efficient mixed protonic-electronic conducting oxides that can act as air electrodes to satisfy high conductivity electrolytes. Despite extensive research efforts in past decades, still remains a trial-and-error process, which extremely time consuming and cost. Herein, based on data acquired from published literature, machine-learning (ML) method introduced accelerate discovery oxides. Accordingly, hydrated proton concentration (HPC) 3200 predicted evaluate conduction essential for enhancing electrochemical performances PCCs. Subsequently, feature importance HPC evaluated establish guideline rapid accurate design high-efficiency Thereafter, screened (La0.7 Ca0.3 )(Co0.8 Ni0.2 )O3 (LCCN7382) prepared, experimental adequately corresponds with results. Moreover, PCC LCCN7382 exhibits satisfactory electrolysis fuel cell modes. In addition promising electrode PCC, this study establishes new avenue ML-based

Язык: Английский

---

Predicting Extraction Selectivity of Acetic Acid in Pervaporation by Machine Learning Models with Data Leakage Management

Environmental Science & Technology, Год журнала: 2023, Номер 57(14), С. 5934 - 5946

Опубликована: Март 27, 2023

The extraction of acetic acid and other carboxylic acids from water is an emerging separation need as they are increasingly produced waste organics CO2 during carbon valorization. However, the traditional experimental approach can be slow expensive, machine learning (ML) may provide new insights guidance in membrane development for organic extraction. In this study, we collected extensive literature data developed first ML models predicting factors between pervaporation with polymers' properties, morphology, fabrication parameters, operating conditions. Importantly, assessed seed randomness leakage problems model development, which have been overlooked studies but will result over-optimistic results misinterpreted variable importance. With proper management, established a robust achieved root-mean-square error 0.515 using CatBoost regression model. addition, prediction was interpreted to elucidate variables' importance, where mass ratio topmost significant factors. concentration membranes' effective area contributed information leakage. These demonstrate models' advances design importance vigorous validation.

Язык: Английский

---

Machine learning exploration of the mobility and environmental assessment of toxic elements in mining-associated solid wastes

Journal of Cleaner Production, Год журнала: 2023, Номер 401, С. 136771 - 136771

Опубликована: Март 11, 2023

Язык: Английский

---

Molecular mechanisms of thickness-dependent water desalination in polyamide reverse-osmosis membranes

Journal of Membrane Science, Год журнала: 2023, Номер 674, С. 121498 - 121498

Опубликована: Фев. 22, 2023

Язык: Английский

---

Deep learning aided inverse design of the buckling-guided assembly for 3D frame structures

Journal of the Mechanics and Physics of Solids, Год журнала: 2023, Номер 179, С. 105398 - 105398

Опубликована: Июль 27, 2023

Язык: Английский

---

Data-driven predictions of complex organic mixture permeation in polymer membranes

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Авг. 15, 2023

Membrane-based organic solvent separations are rapidly emerging as a promising class of technologies for enhancing the energy efficiency existing separation and purification systems. Polymeric membranes have shown promise in fractionation or splitting complex mixtures molecules such crude oil. Determining performance polymer membrane when challenged with mixture has thus far occurred an ad hoc manner, methods to predict based on composition chemistry unavailable. Here, we combine physics-informed machine learning algorithms (ML) mass transport simulations create integrated predictive model containing up 400 components via any arbitrary linear membrane. We experimentally demonstrate effectiveness by predicting two oils within 6-7% measurements. Integration ML predictors diffusion sorption properties simulators enables rapid screening prior physical experimentation liquid mixtures.

Язык: Английский

---

Accelerating Discovery of Polyimides with Intrinsic Microporosity for Membrane‐Based Gas Separation: Synergizing Physics‐Informed Performance Metrics and Active Learning

Advanced Functional Materials, Год журнала: 2024, Номер 34(23)

Опубликована: Фев. 13, 2024

Abstract Polymer membranes are widely used for gas separation, addressing critical environmental and energy issues. Nevertheless, crafting high‐performance polymer remains a challenging task, often relies on labor‐intensive trial‐and‐error experiments. Different from the traditional Edisonian approach, machine learning offers significant potential to expedite design of new yet it faces substantial hurdle due limited data availability. To overcome this challenge, in study two physics‐informed performance metrics introduced, namely fractional free volume average void size, assess separation membranes. By employing active multi‐target screening, top‐performing polyimides with intrinsic microporosity efficiently discovered pool 155 610 candidates, through calculations only 709 (0.45%) entire search space. As validated by molecular simulations, exhibit exceptional CO 2 /N , /CH 4 O mixtures, superior existing polymers surpassing current upper bound. The utilization provides novel strategy advance accelerate discovery many other important applications.

Язык: Английский

---

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

Journal of Membrane Science, Год журнала: 2024, Номер 713, С. 123256 - 123256

Опубликована: Сен. 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.

Язык: Английский

---