skip to main content
10.1145/3653804.3656276acmotherconferencesArticle/Chapter ViewAbstractPublication PagescvdlConference Proceedingsconference-collections
research-article

Machine Learning Framework and Spatiotemporal Variation Analysis for Water Quality Classification in the Xiangjiang Basin

Published: 01 June 2024 Publication History

Abstract

Water quality evaluation classification is a basic task for rational utilization and protection of water resources, and is the basis for water environment management and decision-making. Water quality evaluation involves multiple water quality monitoring indicators which have strong coupling with each other, and these water quality monitoring indicators meet the characteristics of time series. Therefore, to solve the problem of strong coupling, the MLSTM model is used to capture the time dependence of multiple variables in water quality monitoring data, and FCN is used to extract features from water quality monitoring data; At the same time, in order to solve the problem of inaccurate classification caused by imbalanced sample water quality categories in model training, the SMOTE method is used to equalize the sample water quality categories, forming the SMOTE-MLSTM-FCN framework. Through using water quality monitoring data from 9 stations in the main stream of the Xiangjiang River from 2021 to 2022, the result showed that the classification performance of this framework was superior to a single LSTM model. At the Guiyang Town station, the macro F1 score, macro accuracy, macro recall, and accuracy were improved by 25.45%, 25.25%, 24.12%, and 13.02%, respectively. In order to further explore the spatiotemporal changes in the water quality of the Xiangjiang River, the SMOTE-MLSTM-FCN framework was used to classify the water quality monitoring data of various sections in the Xiangjiang River Basin from January to June 2023. Combined with geographic information systems, the spatiotemporal changes of water quality in the Xiangjiang River were analyzed, providing a new technical approach for water quality classification and evaluation.

References

[1]
Chaoxia. Jing, Jun Xia, Xiang Zhang, 2019. Temporal and spatial distribution of water quality in the middle and lower reaches of the Hanjiang River. J. Environmental Scientific Research, vol. 32(1), 104–115. 10.13198/j.issn.1001-6929.2018.07.2
[2]
Colin Lea, Michael D. Flynn, Rene Vidal, Austin Reiter and Gregory D. Hager. 2012. Implementing the water framework directive: a transition from established monitoring networks in England and wales. J. Environmental Science & Policy, vol. 17, 49–61. 10.1016/j.envsci.2011.11.003.
[3]
Xiaogang Han, Yanling Huang, and Xiuzhen Chen. 2013. The improved fuzzy comprehensive evaluation method and its application in raw water quality evaluation of water supply plant. J. Environmental Science & Policy, 33(5), 1513-1518. 10.13671/j.hjkxxb.2013.05.020.
[4]
Xinggui Huang, and Huanhuan Yin. 2022. Analysis on the changing trend and influencing factors of Poyang Lake outlet water quality in recent ten years. J. People's Yangtze River, vol. 53(S2), 15-19+33. 10.16232/j.cnki.1001-4179.2022.S2.004.
[5]
Horton R K. An index-number system for rating water quality. 1965. J. Journal of Water Pollution Control Federation, vol. 37(3), 300-306.
[6]
Ting Zhang, Jingling Liu, and Xuemei Wang. 2010. Evaluation and analysis of temporal and spatial variation of water quality and influencing factors in Baiyangdian Lake. J. Journal of Environmental Science, vol. 30(2), 261-267. 10.13671/j.hjkxxb.2010.02.023.
[7]
Ming Wu, Xiaohu Wen, Qi Feng, 2018. Groundwater quality evaluation of Zhangye Basin in arid oasisarea based on random forest model. J. Chinese Desert, vol. 38(3), 657-663.
[8]
Jiaqi Yao, Shiyi Sun, Haoran Zhai, 2022. Dynamic monitoring of the largest reservoir in North China based on multi-source satellite remote sensing from 2013 to 2022: Water area, water level, water storage and water quality. J. Ecological Indicators, vol. 144, 109470.10.1016/j.ecolind.2022.109470.
[9]
Smail Dilmi, and Mohamed Ladjal. 2021. A novel approach for water quality classification based on the integration of deep learning and feature extraction techniques. J. Chemometrics and Intelligent Laboratory Systems, vol. 214, 104329. 10.1016/j.chemolab.2021.104329.
[10]
Sang-Soo Baek, Jongcheol Pyo, Jong Ahn Chun. 2020. Prediction of water level and water quality using a CNN-LSTM combined Deep Learning approach. J. Water,vol. 12(12), 3399. 10.3390/w12123399.
[11]
Nguyen H. Than, Che D. Ly, and Pham V. Tat. 2021. The performance of classification and forecasting Dong Nai River water quality for sustainable water resources management using neural network techniques. J. Journal of Hydrology, vol. 596, 126099. 10.1016/j.jhydrol.2021.126099.
[12]
Qing Wang. 2011. Research on some key problems in ensemble learning. D. Shanghai: Fudan University, 10-12.
[13]
Wenwu Tan, Jianjun Zhang, Jiang Wu, 2022. Application of CNN and Long Short-Term Memory Network in water quality predicting. J. Intelligent Automation & Soft Computing, vol. 34(3), 1943-1958. 10.32604/iasc.2022.029660
[14]
Yan Zhou. 2022. Text classification method based on GloVe model and attention mechanism Bi-LSTM. J. Electronic Measurement Technology, vol. 45(7), 42-47. 10.19651/j.cnki.emt.2107678.
[15]
Ying L. Xuan, Yuan Wang, and Jia H. 2022 CHEN. LSTM time series classification based on multi-scale convolution and attention mechanism. J. Computer Application, vol. 42(8), 2343-2352.
[16]
Fazle Karim, Somshubra Majumdar, Houshang Darabi, 2018. LSTM Fully Convolutional Networks for Time Series classification. J. IEEE Access, vol. 6, 1662-1669. 10.1109/ACCESS.2017.2779939.
[17]
Dan Hu, Xin Meng, Shuai Lu, 2022. Application of a parallel LSTM-FCN model in ship track prediction. J. Control and Decision, vol. 37(8), 1955-1961. 10.13195/j.kzyjc.2020.1795.
[18]
Jianming Xiong. 2022.Detection and early warning of students' psychological abnormality based on Time Series classification. D. Xi 'an: Northwest University, 9-11. 10.27405/d.cnki.gxbdu.2022.000209
[19]
Tingting Xu, Giovanni Coco, and Martin Neale. 2020. A predictive model of recreational water quality based on adaptive synthetic sampling algorithms and Machine Learning. J. Water Research, vol. 177, 115788. 10.1016/j.watres.2020.115788.
[20]
Chun-ling Lai. 2020. Fault diagnosis research and software development based on unbalanced wastewater treatment data. D. South China University of Technology. 10.27151/d.cnki.ghnlu.2019.003529.
[21]
Jie Cai, Jiawei Luo, Shulin Wang, 2018. Feature selection in Machine Learning: A New Perspective. J. Neurocomputing, vol. 300, 70-79. 10.1016/j.neucom.2017.11.077.
[22]
Haitao Yang. 2020. Imbalanced Classification Data Based on Generative Adversarial Nets. D. Beijing University of Posts and Telecommunications.
[23]
Peng Chu, Xiao Bian, Shaopeng Liu, and Haibin Ling. 2020. Feature Space Augmentation for Long-Tailed Data. in Computer Vision – ECCV, vol. 12374, 694–710. 10.1007/978-3-030-58526-6_41.
[24]
Julián Luengo, Alberto Fernández, Salvador García and Francisco Herrera. 2011. Addressing data complexity for imbalanced data sets: analysis of SMOTE-based oversampling and evolutionary undersampling. J. Soft Computing, vol. 15(10), 1909-1936.
[25]
Ling Xu, Xiangnan Jing, Ying Yang, 2023. Classification and evaluation of national surface water quality based on SMOTE-GA-CatBoost algorithm. J. Chinese Environmental Science, 1-11. 10.19674/j.cnki.issn1000-6923.20230221.033.
[26]
Y. Lecun, L. Bottou, Y. Bengio, 1998. Gradient-based learning applied to document recognition. J. Proceedings of the IEEE, vol. 86(11), 2278-2324. 10.1109/5.726791.
[27]
Bingzhen Li, Ke Liu, Jiaojiao Gu, 2021. Review of convolutional Neural Networks. J. Computer Age, vol. 2021(4), 8-12+17.
[28]
Evan Shelhamer, Jonathan Long, and Trevor Darrell. 2017. Fully Convolutional Networks for semantic segmentation. J. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39(4), 640-651.
[29]
Zhiguang Wang, Weizhong Yan, and Tim Oates. 2017. Time Series classification from scratch with deep Neural Networks: a strong baseline. J. International Joint Conference on Neural Networks (IJCNN), 1578-1585. 10.1109/IJCNN.2017.7966039.
[30]
S. Hochreiter, J. Schmidhuber. 1997. Long Short-Term Memory. J. Neural Computation, vol. 9(8), 1735-1780.
[31]
Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford. 2019. Multivariate LSTM-FCNs for Time Series classification. J. Neural Networks, vol. 116, 237-245. 10.1016/j.neunet.2019.04.014.
[32]
Ministry of Ecology and Environment. Surface water environmental quality standard: GB 3838-2002[S]. Beijing: China Standards Publishing Society, 2002.
[33]
Jianjun Zhang, Yifu Sheng, Weida Chen, 2020. Design and analysis of a water quality monitoring data service platform. J. Computers, Materials & Continua, vol. 66(1), 389-405. 10.32604/cmc.2020.012384.
[34]
M. Bach, A. Werner, J. Żywiec, 2017. The study of under- and over-sampling methods’ utility in analysis of highly imbalanced data on osteoporosis. J. Information Sciences, vol. 384, 174-190. 10.1016/j.ins.2016.09.038.
[35]
Jie Hu, Li Shen, Gang Sun. 2018. Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7132-7141. 10.1109/CVPR.2018.00745.
[36]
Colin Lea, Rene Vidal, Austin Reiter, Gregory D.Hager, 2017. Temporal Convolutional Networks for action segmentation and detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1003-1012. 10.1109/CVPR.2017.113.
[37]
Sergey Ioffe, and Christian Szegedy. 2015. Batch Normalization: accelerating Deep Network training by reducing internal covariate shift. 2015 Christian Szegedy Proceedings of the 32nd International Conference on Machine Learning (PMLR), 448-456. 10.48550/ARXIV.1502.03167.
[38]
Ludovic Trottier, Philippe Giguere and Brahim Chaib-draa. 2017. Parametric exponential linear unit for Deep Convolutional Neural Networks. 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), 207-214. 10.1109/ICMLA.2017.00038.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
CVDL '24: Proceedings of the International Conference on Computer Vision and Deep Learning
January 2024
506 pages
ISBN:9798400718199
DOI:10.1145/3653804
Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of a national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 June 2024

Permissions

Request permissions for this article.

Check for updates

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

CVDL 2024

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 14
    Total Downloads
  • Downloads (Last 12 months)14
  • Downloads (Last 6 weeks)1
Reflects downloads up to 13 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media