Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy

Chemical oxygen demand (COD) is a critical parameter employed to assess the level of organic pollution in water. Accurate COD detection is essential for effective environmental monitoring and water quality assessment. Ultraviolet–visible (UV-Vis) spectroscopy has become a widely applied method for C...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingwei Li, Yijing Lu, Yipei Ding, Chenxuan Zhou, Jia Liu, Zhiyu Shao, Yibei Nian
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/3/191
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089958797213696
author Jingwei Li
Yijing Lu
Yipei Ding
Chenxuan Zhou
Jia Liu
Zhiyu Shao
Yibei Nian
author_facet Jingwei Li
Yijing Lu
Yipei Ding
Chenxuan Zhou
Jia Liu
Zhiyu Shao
Yibei Nian
author_sort Jingwei Li
collection DOAJ
description Chemical oxygen demand (COD) is a critical parameter employed to assess the level of organic pollution in water. Accurate COD detection is essential for effective environmental monitoring and water quality assessment. Ultraviolet–visible (UV-Vis) spectroscopy has become a widely applied method for COD detection due to its convenience and the absence of the need for chemical reagents. This non-destructive and reagent-free approach offers a rapid and reliable means of analyzing water. Recently, deep learning has emerged as a powerful tool for automating the process of spectral feature extraction and improving COD prediction accuracy. In this paper, we propose a novel multi-scale one-dimensional convolutional neural network (MS-1D-CNN) fusion model designed specifically for spectral feature extraction and COD prediction. The architecture of the proposed model involves inputting raw UV-Vis spectra into three parallel sub-1D-CNNs, which independently process the data. The outputs from the final convolution and pooling layers of each sub-CNN are then fused into a single layer, capturing a rich set of spectral features. This fused output is subsequently passed through a Flatten layer followed by fully connected layers to predict the COD value. Experimental results demonstrate the effectiveness of the proposed method, as it was compared with three traditional methods and three deep learning methods on the same dataset. The MS-1D-CNN model showed a significant improvement in the accuracy of COD prediction, highlighting its potential for more reliable and efficient water quality monitoring.
format Article
id doaj-art-afc2b6d5287a43b288e4c04a836d0309
institution DOAJ
issn 2313-7673
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-afc2b6d5287a43b288e4c04a836d03092025-08-20T02:42:39ZengMDPI AGBiomimetics2313-76732025-03-0110319110.3390/biomimetics10030191Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible SpectroscopyJingwei Li0Yijing Lu1Yipei Ding2Chenxuan Zhou3Jia Liu4Zhiyu Shao5Yibei Nian6School of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaSchool of Electrical, Energy and Power Engineering, Yangzhou University, No. 88 South University Road, Yangzhou 225009, ChinaChemical oxygen demand (COD) is a critical parameter employed to assess the level of organic pollution in water. Accurate COD detection is essential for effective environmental monitoring and water quality assessment. Ultraviolet–visible (UV-Vis) spectroscopy has become a widely applied method for COD detection due to its convenience and the absence of the need for chemical reagents. This non-destructive and reagent-free approach offers a rapid and reliable means of analyzing water. Recently, deep learning has emerged as a powerful tool for automating the process of spectral feature extraction and improving COD prediction accuracy. In this paper, we propose a novel multi-scale one-dimensional convolutional neural network (MS-1D-CNN) fusion model designed specifically for spectral feature extraction and COD prediction. The architecture of the proposed model involves inputting raw UV-Vis spectra into three parallel sub-1D-CNNs, which independently process the data. The outputs from the final convolution and pooling layers of each sub-CNN are then fused into a single layer, capturing a rich set of spectral features. This fused output is subsequently passed through a Flatten layer followed by fully connected layers to predict the COD value. Experimental results demonstrate the effectiveness of the proposed method, as it was compared with three traditional methods and three deep learning methods on the same dataset. The MS-1D-CNN model showed a significant improvement in the accuracy of COD prediction, highlighting its potential for more reliable and efficient water quality monitoring.https://www.mdpi.com/2313-7673/10/3/191UV-Vis spectroscopyCODone-dimensional convolutional neural network
spellingShingle Jingwei Li
Yijing Lu
Yipei Ding
Chenxuan Zhou
Jia Liu
Zhiyu Shao
Yibei Nian
Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
Biomimetics
UV-Vis spectroscopy
COD
one-dimensional convolutional neural network
title Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
title_full Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
title_fullStr Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
title_full_unstemmed Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
title_short Prediction of Water Chemical Oxygen Demand with Multi-Scale One-Dimensional Convolutional Neural Network Fusion and Ultraviolet–Visible Spectroscopy
title_sort prediction of water chemical oxygen demand with multi scale one dimensional convolutional neural network fusion and ultraviolet visible spectroscopy
topic UV-Vis spectroscopy
COD
one-dimensional convolutional neural network
url https://www.mdpi.com/2313-7673/10/3/191
work_keys_str_mv AT jingweili predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT yijinglu predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT yipeiding predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT chenxuanzhou predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT jialiu predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT zhiyushao predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy
AT yibeinian predictionofwaterchemicaloxygendemandwithmultiscaleonedimensionalconvolutionalneuralnetworkfusionandultravioletvisiblespectroscopy