DOI: 10.1016/j.watres.2018.02.052
Scopus记录号: 2-s2.0-85042691938
论文题名: Neural networks for dimensionality reduction of fluorescence spectra and prediction of drinking water disinfection by-products
作者: Peleato N.M. ; Legge R.L. ; Andrews R.C.
刊名: Water Research
ISSN: 431354
出版年: 2018
卷: 136 起始页码: 84
结束页码: 94
语种: 英语
英文关键词: Autoencoder
; Dimensionality reduction
; Disinfection by-products
; Fluorescence spectroscopy
; Neural networks
; Water treatment
Scopus关键词: Biogeochemistry
; Biological materials
; Data reduction
; Disinfection
; Fluorescence
; Fluorescence spectroscopy
; Fluorophores
; Forecasting
; Learning systems
; Neural networks
; Organic compounds
; Potable water
; Water treatment
; Auto encoders
; Dimensionality reduction
; Dimensionality reduction techniques
; Disinfection by-product
; Drinking water disinfection
; Improved predictability
; Parallel factors analysis
; Regression techniques
; Principal component analysis
; drinking water
; organic matter
; river water
; drinking water
; artificial neural network
; byproduct
; disinfection
; drinking water
; equipment
; fluorescence
; fluorescence spectroscopy
; prediction
; spectral analysis
; water treatment
; Article
; artificial neural network
; disinfection
; fluorescence spectroscopy
; parallel design
; prediction
; principal component analysis
; priority journal
; water quality
; chemistry
; devices
; disinfection
; fluorescence
; procedures
; water management
; water pollutant
; Disinfection
; Drinking Water
; Fluorescence
; Neural Networks (Computer)
; Water Pollutants, Chemical
; Water Purification
英文摘要: The use of fluorescence data coupled with neural networks for improved predictability of drinking water disinfection by-products (DBPs) was investigated. Novel application of autoencoders to process high-dimensional fluorescence data was related to common dimensionality reduction techniques of parallel factors analysis (PARAFAC) and principal component analysis (PCA). The proposed method was assessed based on component interpretability as well as for prediction of organic matter reactivity to formation of DBPs. Optimal prediction accuracies on a validation dataset were observed with an autoencoder-neural network approach or by utilizing the full spectrum without pre-processing. Latent representation by an autoencoder appeared to mitigate overfitting when compared to other methods. Although DBP prediction error was minimized by other pre-processing techniques, PARAFAC yielded interpretable components which resemble fluorescence expected from individual organic fluorophores. Through analysis of the network weights, fluorescence regions associated with DBP formation can be identified, representing a potential method to distinguish reactivity between fluorophore groupings. However, distinct results due to the applied dimensionality reduction approaches were observed, dictating a need for considering the role of data pre-processing in the interpretability of the results. In comparison to common organic measures currently used for DBP formation prediction, fluorescence was shown to improve prediction accuracies, with improvements to DBP prediction best realized when appropriate pre-processing and regression techniques were applied. The results of this study show promise for the potential application of neural networks to best utilize fluorescence EEM data for prediction of organic matter reactivity. © 2018 Elsevier Ltd Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/112848
Appears in Collections: 气候减缓与适应
There are no files associated with this item.
作者单位: Department of Civil Engineering, University of Toronto, 35 St. George St., Toronto, Ontario M5S 1A4, Canada; Department of Chemical Engineering, University of Waterloo, 200 University Ave., Waterloo, Ontario N2L 3G1, Canada
Recommended Citation:
Peleato N.M.,Legge R.L.,Andrews R.C.. Neural networks for dimensionality reduction of fluorescence spectra and prediction of drinking water disinfection by-products[J]. Water Research,2018-01-01,136