Laser induced breakdown spectroscopy combined with hybrid variable selection for the prediction of the environmental risk Nemerow index of heavy metals in oily sludge

Li, Maogang; Fu, Han; Du, Yanyan; Huang, Xuan; Zhang, Tianlong; Tang, Hongsheng; Li, Hua

doi:10.1039/d2ja00048b

Cited by 16 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To allow practical applications, operationally defined criteria were proposed for environmental risk assessment of oily sludge, particularly heavy metals in original oily sludge or the sludge residues from either pyrolytic or incineration treatments. Li et al [41] developed a prediction method for assessing the risk level of heavy metals in oily sludge using laser-induced breakdown spectroscopy (LIBS) combined with hybrid variable selection. They determined the LIBS spectra of 30 oily sludge samples and calculated the corresponding Nemerow index.…”

Section: Environmental Impacts Of Oily Sludgementioning

confidence: 99%

Trend in Research on Characterization, Environmental Impacts and Treatment of Oily Sludge: A Systematic Review

Niu¹,

Sun²,

Lin

2022

Molecules

View full text Add to dashboard Cite

Oily sludge is a hazardous material generated from the petroleum industry that has attracted increasing research interest. Although several review articles have dealt with specific subtopics focusing on the treatment of oily sludge based on selected references, no attempt has been made to demonstrate the research trend of oily sludge comprehensively and quantitatively. This study conducted a systematic review to analyze and evaluate all oily sludge-related journal articles retrieved from the Web of Science database. The results show that an increase in oily sludge-related research did not take place until recent years and the distribution of the researchers is geographically out of balance. Most oily sludge-related articles focused on treatment for harmfulness reduction or valorization with limited coverage of formation, characterization, and environmental impact assessment of oily sludge. Pyrolytic treatment has attracted increasing research attention in recent years. So far, the research findings have been largely based on laboratory-scale experiments with insufficient consideration of the cost-effectiveness of the proposed treatment methods. Although many methods have been proposed, few alone could satisfactorily achieve cost-effective treatment goals. To enable sustainable management of oily sludge on a global scale, efforts need to be made to fund more research projects, especially in the major oil-producing countries. Pilot-scale experiments using readily available and affordable materials should be encouraged for practical purposes. This will allow a sensible cost-benefit analysis of a proposed method/procedure for oily sludge treatment. To improve the treatment performance, combined methods are more desirable. To inform the smart selection of methods for the treatment of different oily sludge types, it is suggested to develop universally accepted evaluation systems for characterization and environmental risk of oily sludge.

show abstract

Section: Environmental Impacts Of Oily Sludgementioning

confidence: 99%

Trend in Research on Characterization, Environmental Impacts and Treatment of Oily Sludge: A Systematic Review

Niu¹,

Sun²,

Lin

2022

Molecules

View full text Add to dashboard Cite

show abstract

“…Purely data-driven variable selection has attracted increasing interest in LIBS quantification [18,19]. Important variables related to quantitative information are automatically identified, and multivariate models based on these variables can yield higher prediction accuracy than multivariate models based on empirical variables [20]. Some widely used variable selection methods include Pearson's…”

Section: Introductionmentioning

confidence: 99%

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

LYU 吕,

SONG 宋,

HOU 侯

et al. 2024

Plasma Sci. Technol.

View full text Add to dashboard Cite

Nowadays, laser-induced breakdown spectroscopy (LIBS) has become a widely used atomic spectroscopic technique for rapid coal analysis. While the vast spectral information in LIBS contains signal uncertainty, which can impact its quantification performance. In this work, we proposed a hybrid variable selection method to improve the performance of LIBS quantification. Important variables are first identified using Pearson’s correlation coefficient (PCC), mutual information (MI), least absolute shrinkage and selection operator (LASSO) and random forest (RF), and then filtered and combined with empirical variables related to fingerprint elements of coal ash content. Subsequently, these variables are fed into partial least squares regression (PLSR). Additionally, in some models, certain variables unrelated to ash content were removed manually to study the variable deselection’s impact on model performance. The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method. It is significantly better than the variable selection only based on empirical knowledge and in most cases outperforms the baseline method. The results showed that on all three datasets, hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest RMSEP values of 1.605, 3.478 and 1.647, respectively, which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables, which are 1.959, 3.718 and 2.181, respectively. The EMP-LASSO-PLSR model with 20 selected variables exhibited a significant improving performance after variable deselection, with RMSEP values dropping from 1.635, 3.962, 1.647 to 1.483, 3.086, 1.567, respectively. Such results demonstrate that using empirical knowledge as a support to data-driven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

show abstract

“…The LIBS information is very complex because of the complex matrix of rare earth ore, which reduces the accuracy of LIBS technology in the analysis of rare earths. Chemometrics analysis methods, such as partial least squares (PLS), 28 random forest (RF), 29–31 artificial neural networks (ANN), 32 support vector machine (SVM), 33 and other algorithms, provide effective tools for accurate quantitative analysis of LIBS technology. PLS is one of the most commonly used modeling methods in chemometrics.…”

Section: Introductionmentioning

confidence: 99%

Rapid quantitative analysis of rare earth elements Lu and Y in rare earth ores by laser induced breakdown spectroscopy combined with iPLS-VIP and partial least squares

Liu

Yan

et al. 2023

RSC Adv.

Self Cite

View full text Add to dashboard Cite

show abstract

Laser induced breakdown spectroscopy combined with hybrid variable selection for the prediction of the environmental risk Nemerow index of heavy metals in oily sludge

Abstract: Oily sludge is an associated pollutant in crude oil exploitation, transportation, processing and subsequent treatment, which contains a large number of toxic components, including heavy metals, aromatic hydrocarbons, aged crude...

Cited by 16 publications

References 47 publications

Trend in Research on Characterization, Environmental Impacts and Treatment of Oily Sludge: A Systematic Review

Trend in Research on Characterization, Environmental Impacts and Treatment of Oily Sludge: A Systematic Review

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Rapid quantitative analysis of rare earth elements Lu and Y in rare earth ores by laser induced breakdown spectroscopy combined with iPLS-VIP and partial least squares

Contact Info

Product

Resources

About