Deep spatial representation learning of polyamide nanofiltration membranes

Zhang, Ziyang; Luo, Yingtao; Peng, Huawen; Chen, Yu; Liao, Rong‐Zhen; Zhen, Qiang

doi:10.1016/j.memsci.2020.118910

Cited by 20 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core component of membrane separation technology is a natural or synthetic filter membrane, which has good selective permeability, and can separate, purify, and enrich two-component or multi-component solutes and solvents through external energy or chemical potential difference as the driving force. At present, filter membranes can be divided into five categories according to driving pressure ( Table 1 ) which are microfiltration (MF) [ 3 ], ultrafiltration (UF) [ 48 ], nanofiltration (NF) [ 49 ], reverse osmosis (RO) [ 50 ], and forward osmosis (FO) [ 51 ]. Compared with the forward osmosis where the driving force is the penetration pressure difference on both sides of the solution, the reverse osmosis technique is that the solvent overcomes the pressure difference driven by an external force.…”

Section: Nanocellulose Filtration Membranementioning

confidence: 99%

Nanocellulose Based Filtration Membrane in Industrial Waste Water Treatment: A Review

Liu

Shen

2021

Materials

View full text Add to dashboard Cite

In the field of industrial wastewater treatment, membrane separation technology, as an emerging separation technology, compared with traditional separation technology such as precipitation, adsorption, and ion exchange, has advantages in separation efficiency, low energy consumption, low cost, simple operation, and no secondary pollution. The application has been expanding in recent years, but membrane fouling and other problems have seriously restricted the development of membrane technology. Natural cellulose is one of the most abundant resources in nature. In addition, nanocellulose has characteristics of high strength and specific surface area, surface activity groups, as well as being pollution-free and renewable, giving it a very wide development prospect in many fields, including membrane separation technology. This paper reviews the current status of nanocellulose filtration membrane, combs the widespread types of nanocellulose and its derivatives, and summarizes the current application of cellulose in membrane separation. In addition, for the purpose of nanocellulose filtration membrane in wastewater treatment, nanocellulose membranes are divided into two categories according to the role in filtration membrane: the application of nanocellulose as membrane matrix material and as a modified additive in composite membrane in wastewater treatment. Finally, the advantages and disadvantages of inorganic ceramic filtrations and nanocellulose filtrations are compared, and the application trend of nanocellulose in the filtration membrane direction is summarized and discussed.

show abstract

Section: Nanocellulose Filtration Membranementioning

confidence: 99%

Nanocellulose Based Filtration Membrane in Industrial Waste Water Treatment: A Review

Liu

Shen

2021

Materials

View full text Add to dashboard Cite

show abstract

“…The ML algorithms have been utilized to understand nonlinear relationships between input variables and outputs in the fields of environmental science and engineering, including membrane desalination. ,,,,, Due to the “black box” nature of ML models, the explainability of these models is essential to investigating the reliability of the decision-making process. XAI is able to reveal the decision-making process of ML models and enhances the trust in the models .…”

Section: Resultsmentioning

confidence: 99%

Exploring the Knowledge Attained by Machine Learning on Ion Transport across Polyamide Membranes Using Explainable Artificial Intelligence

Jeong

Epsztein

Wang

et al. 2023

Environ. Sci. Technol.

View full text Add to dashboard Cite

Recent studies have increasingly applied machine learning (ML) to aid in performance and material design associated with membrane separation. However, whether the knowledge attained by ML with a limited number of available data is enough to capture and validate the fundamental principles of membrane science remains elusive. Herein, we applied explainable artificial intelligence (XAI) to thoroughly investigate the knowledge learned by ML on the mechanisms of ion transport across polyamide reverse osmosis (RO) and nanofiltration (NF) membranes by leveraging 1,585 data from 26 membrane types. The Shapley additive explanation method based on cooperative game theory was used to unveil the influences of various ion and membrane properties on the model predictions. XAI shows that the ML can capture the important roles of size exclusion and electrostatic interaction in regulating membrane separation properly. XAI also identifies that the mechanisms governing ion transport possess different relative importance to cation and anion rejections during RO and NF filtration. Overall, we provide a framework to evaluate the knowledge underlying the ML model prediction and demonstrate that ML is able to learn fundamental mechanisms of ion transport across polyamide membranes, highlighting the importance of elucidating model interpretability for more reliable and explainable ML applications to membrane selection and design.

show abstract

“…The salt rejection and the water flux are the two major desalination performance evaluation metrics of membranes to be predicted by ML. In the work of Zhang et al, 19 the authors proposed a featurization strategy of polyamide membranes for rejection and flux prediction. The features of the membranes included the type of supporting membrane, chemical structure (Cartesian atom coordinates calculated by density functional theory), concentration of the monomer of polyamide membrane, and operation pressure of the nanofiltration.…”

Section: ■ ML For Membrane Property Predictionmentioning

confidence: 99%

Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization

Cao,

Barati Farimani,

Ock

et al. 2024

Nano Lett.

View full text Add to dashboard Cite

Porous membranes, either polymeric or two-dimensional materials, have been extensively studied because of their outstanding performance in many applications such as water filtration. Recently, inspired by the significant success of machine learning (ML) in many areas of scientific discovery, researchers have started to tackle the problem in the field of membrane design using data-driven ML tools. In this Mini Review, we summarize research efforts on three types of applications of machine learning in membrane design, including (1) membrane property prediction using ML, (2) gaining physical insight and drawing quantitative relationships between membrane properties and performance using explainable artificial intelligence, and (3) ML-guided design, optimization, or virtual screening of membranes. On top of the review of previous research, we discuss the challenges associated with applying ML for membrane design and potential future directions.

show abstract

Deep spatial representation learning of polyamide nanofiltration membranes

Cited by 20 publications

References 42 publications

Nanocellulose Based Filtration Membrane in Industrial Waste Water Treatment: A Review

Nanocellulose Based Filtration Membrane in Industrial Waste Water Treatment: A Review

Exploring the Knowledge Attained by Machine Learning on Ion Transport across Polyamide Membranes Using Explainable Artificial Intelligence

Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization

Contact Info

Product

Resources

About