2022
DOI: 10.1080/01614940.2022.2082650
|View full text |Cite
|
Sign up to set email alerts
|

Application of machine learning algorithms in predicting the photocatalytic degradation of perfluorooctanoic acid

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
12
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 24 publications
(13 citation statements)
references
References 71 publications
0
12
0
Order By: Relevance
“…In addition to the battery sector, machine learning plays an important role in the prediction of degradation of other materials. For example, to estimate the photocatalytic decomposition of PFOA on various photocatalysts, different ML algorithms, including multiple linear regression (MLR), random forest (RF), ridge regression (RR), multilayer perceptron (MLP), gradient boosting machine (GBM), adaptive boosting (AdaBoost) and support vector machine (SVM), were used by Li et al [ 102 ] to nominate a potential and effective method. After considering numerous factors, such as solution pH, solution temperature, catalyst dose, light irradiation intensity, irradiation wavelength, irradiation duration, initial PFOA concentration, type of catalyst, and oxidizing agents, the GBM model was found to give better results than other models.…”
Section: Performance Predictionmentioning
confidence: 99%
“…In addition to the battery sector, machine learning plays an important role in the prediction of degradation of other materials. For example, to estimate the photocatalytic decomposition of PFOA on various photocatalysts, different ML algorithms, including multiple linear regression (MLR), random forest (RF), ridge regression (RR), multilayer perceptron (MLP), gradient boosting machine (GBM), adaptive boosting (AdaBoost) and support vector machine (SVM), were used by Li et al [ 102 ] to nominate a potential and effective method. After considering numerous factors, such as solution pH, solution temperature, catalyst dose, light irradiation intensity, irradiation wavelength, irradiation duration, initial PFOA concentration, type of catalyst, and oxidizing agents, the GBM model was found to give better results than other models.…”
Section: Performance Predictionmentioning
confidence: 99%
“…Nanopowder-based coatings with a thickness of several micrometres have a milky non-transparent surface. 6 Despite this, several studies have been conducted on TiO 2 thin films and coatings, 3–13 and still higher photocatalytic activity has been achieved using thick coatings prepared from TiO 2 nanopowders. 7–9 In particular, Zou and co-authors obtained 55% conversion of 100 ppm of toluene after 60 min of ultraviolet (UV-A) irradiation on a 7 μm-thick TiO 2 coating prepared from P25 powder.…”
Section: Introductionmentioning
confidence: 99%
“…12 Thus, the deposition of well-adhered photocatalysts in the form of thick or thin films onto a substrate, such as glass or stainless steel depending on its destined application, is the most viable strategy for the technological application of photocatalytic nanomaterials in any field, and especially in the environmental sector. 12,13 Polycrystalline TiO 2 thin films synthesized from a Ti-alkoxide precursor solution deposited by sol–gel spin/dip coating or spray pyrolysis methods is an old established route 14 and it profits from lower quantities of materials (<1 mg cm −2 ), good adhesion properties and optical transparency in the visible range. 10,13,15 Photocatalysts in the form of thin or thick films possess another advantage over nanopowders, making them applicable as multifunctional surfaces for photocatalytic VOC degradation: antimicrobial and self-cleaning properties.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations