Insights on features' contribution to desalination dynamics and capacity of capacitive deionization through machine learning study

Saffarimiandoab, Farzin; Mattesini, Riccardo; Fu, Wanyi; Kuruoğlu, Erçan E.; Zhang, Xihui

doi:10.1016/j.desal.2021.115197

Cited by 27 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the descriptors and their relationship with the material properties are analyzed (Figure 13d), an inverse‐design approach can also be used. [ 275,276 ]…”

Section: Machine Learningmentioning

confidence: 99%

“…Because the descriptors and their relationship with the material properties are analyzed (Figure 13d), an inverse-design approach can also be used. [275,276] The screening and prediction of material elements using ML models have been applied to a wide range of materials, including metal alloys, [277] MOFs, [30,278] semiconductors, [271,272,279] and polymers. [274,280] Their application range also extends widely from gas storage, [278] separation, [30,[274][275][276] electrode, [281] and even drug delivery systems.…”

Section: Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

Extreme Ion‐Transport Inorganic 2D Membranes for Nanofluidic Applications

et al. 2023

View full text Add to dashboard Cite

Inorganic 2D materials offer a new approach to controlling mass diffusion at the nanoscale. Controlling ion transport in nanofluidics is key to energy conversion, energy storage, water purification, and numerous other applications wherein persistent challenges for efficient separation must be addressed. The recent development of 2D membranes in the emerging field of energy harvesting, water desalination, and proton/Li‐ion production in the context of green energy and environmental technology is herein discussed. The fundamental mechanisms, 2D membrane fabrication, and challenges toward practical applications are highlighted. Finally, the fundamental issues of thermodynamics and kinetics are outlined along with potential membrane designs that must be resolved to bridge the gap between lab‐scale experiments and production levels.

show abstract

“…Because the descriptors and their relationship with the material properties are analyzed (Figure 13d), an inverse‐design approach can also be used. [ 275,276 ]…”

Section: Machine Learningmentioning

confidence: 99%

Section: Machine Learningmentioning

confidence: 99%

Extreme Ion‐Transport Inorganic 2D Membranes for Nanofluidic Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…† This is because of the repulsive Pauli interaction force, with a factor of r −12 , between water molecules and the carbon atoms of the CNT wall, which constrains the effective diameter (d eff ). This diameter was calculated using eqn (5) and is listed in Table 1.…”

Section: Electrolyte Structure Inside the Cnt Electrodesmentioning

confidence: 99%

“…Shim and Kim 32 simulated supercapacitors with CNT electrodes and ionic liquid electrolyte. They found that the specic capacitance of the system increases when the CNT's diameter decreases from (15,15) to (7,7) and it diminishes when the diameter reduces further from (6,6) to (5,5). In the case of supercapacitors with a slit pore, the capacitance was reported to show an oscillatory behavior with respect to the pore size with a minimum value of the pore size of $9 Å and increasing specic capacitance from the pore size of $9 Å to $7 Å.…”

Section: Charging Properties Energy Storage and Charge Efficienciesmentioning

confidence: 99%

“…The main step in desalination is the separation of the ionic content and water from each other. Various techniques on a laboratory scale or industrial pilot scale including membrane-based reverse osmosis and forward osmosis processes, 1,2 thermal distillation-based processes, 3 electrodialysis and capacitive deionization (CDI) process 4,5 have been developed and practiced for this purpose over the globe. The CDI process is a promising technique that has attracted much attention for being an environmentally friendly and feasible process and operation under ambient conditions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Molecular insights into capacitive deionization mechanisms inside hydrophobic and hydrophilic carbon nanotube channel electrodes

2022

Self Cite

View full text Add to dashboard Cite

show abstract

Machine Learning‐Guided Prediction of Desalination Capacity and Rate of Porous Carbons for Capacitive Deionization

Wang,

Jiang,

et al. 2024

Small

View full text Add to dashboard Cite

Nowadays, capacitive deionization (CDI) has emerged as a prominent technology in the desalination field, typically utilizing porous carbons as electrodes. However, the precise significance of electrode properties and operational conditions in shaping desalination performance remains blurry, necessitating numerous time‐consuming and resource‐intensive CDI experiments. Machine learning (ML) presents an emerging solution, offering the prospect of predicting CDI performance with minimal investment in electrode material synthesis and testing. Herein, four ML models are used for predicting the CDI performance of porous carbons. Among them, the gradient boosting model delivers the best performance on test set with low root mean square error values of 2.13 mg g−1 and 0.073 mg g−1 min−1 for predicting desalination capacity and rate, respectively. Furthermore, SHapley Additive exPlanations is introduced to analyze the significance of electrode properties and operational conditions. It highlights that electrolyte concentration and specific surface area exert a substantially more influential role in determining desalination performance compared to other features. Ultimately, experimental validation employing metal–organic frameworks‐derived porous carbons and biomass‐derived porous carbons as CDI electrodes is conducted to affirm the prediction accuracy of ML models. This study pioneers ML techniques for predicting CDI performance, offering a compelling strategy for advancing CDI technology.

show abstract

Insights on features' contribution to desalination dynamics and capacity of capacitive deionization through machine learning study

Cited by 27 publications

References 65 publications

Extreme Ion‐Transport Inorganic 2D Membranes for Nanofluidic Applications

Extreme Ion‐Transport Inorganic 2D Membranes for Nanofluidic Applications

Molecular insights into capacitive deionization mechanisms inside hydrophobic and hydrophilic carbon nanotube channel electrodes

Machine Learning‐Guided Prediction of Desalination Capacity and Rate of Porous Carbons for Capacitive Deionization

Contact Info

Product

Resources

About