A PCA–EEMD–CNN–Attention–GRU–Encoder–Decoder Accurate Prediction Model for Key Parameters of Seawater Quality in Zhanjiang Bay
Abstract
:1. Introduction
2. PCA–EEMD–CNN–Attention–GED Prediction Model
2.1. Network Input Module
2.2. Feature Extraction Module
2.3. Attention–GED Attention Module
2.3.1. Temporal Attention
2.3.2. Spatial Attention
2.4. Network Output Module
3. Results and Analysis
3.1. Experimental Data Acquisition
3.2. Parameter Setting and Evaluation Index
3.3. Data Processing and Analysis
3.4. Ablation Experiments
3.5. Comparison Experiments
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Albasri, H.; Sagala, S.; Pratama, I.; Sammut, J. An improved prioritization framework for selecting new finfish mariculture candidates for research and development in Indonesia. Aquac. Res. 2020, 51, 1464–1479. [Google Scholar] [CrossRef]
- Fu, D.; Zhong, Y.; Chen, F.; Yu, G.; Zhang, X. Analysis of Dissolved Oxygen and Nutrients in Zhanjiang Bay and the Adjacent Sea Area in Spring. Sustainability 2020, 12, 889. [Google Scholar] [CrossRef] [Green Version]
- Bosma, R.; Verdegem, M. Sustainable aquaculture in ponds: Principles, practices and limits. Livest. Sci. 2011, 139, 58–68. [Google Scholar] [CrossRef]
- Ojeda, C.B.; Rojas, F.S. Process Analytical Chemistry: Applications of Ultraviolet/Visible Spectrometry in Environmental Analysis: An Overview. Appl. Spectrosc. Rev. 2009, 44, 245–265. [Google Scholar] [CrossRef]
- Su, X.; Sutarlie, L.; Loh, X. Sensors, Biosensors, and Analytical Technologies for Aquaculture Water Quality. Research 2020, 9, 331–345. [Google Scholar] [CrossRef] [Green Version]
- Liu, S.-S.; He, Z.; Yang, G.-P. Bromoform, dibromochloromethane, and dibromomethane over the East China Sea and the western Pacific Ocean: Oceanic emission and spatial variation. Chemosphere 2020, 257, 127151. [Google Scholar] [CrossRef]
- Sun, X.; Wang, X.; Cai, D.; Li, Z.; Gao, Y. Multivariate Seawater Quality Prediction Based on PCA-RVM Supported by Edge Computing towards Smart Ocean. IEEE Access 2020, 8, 54506–54513. [Google Scholar] [CrossRef]
- Pandey, P.; Bokde, N.; Dongre, S.; Gupta, R. Hybrid Models for Water Demand Forecasting. J. Water Resour. Plan. Manag. 2021, 147, 04020106. [Google Scholar] [CrossRef]
- Raj, N.; Brown, J. An EEMD-BiLSTM Algorithm Integrated with Boruta Random Forest Optimiser for Significant Wave Height Forecasting along Coastal Areas of Queensland, Australia. Remote Sens. 2021, 13, 1456. [Google Scholar] [CrossRef]
- Zhang, Y.; Fitch, P.; Thorburn, P. Predicting the Trend of Dissolved Oxygen Based on the kPCA-RNN Model. Water 2020, 12, 585. [Google Scholar] [CrossRef] [Green Version]
- Li, D.; Wang, X.; Sun, J.; Feng, Y. Radial Basis Function Neural Network Model for Dissolved Oxygen Concentration Prediction Based on an Enhanced Clustering Algorithm and Adam. IEEE Access 2021, 9, 44521–44533. [Google Scholar] [CrossRef]
- Cao, S.; Zhou, L.; Zhang, Z. Prediction of Dissolved Oxygen Content in Aquaculture Based on Clustering and Improved ELM. IEEE Access 2021, 9, 135508–135512. [Google Scholar] [CrossRef]
- Wang, L.; Jiang, Y.; Qi, H. Marine Dissolved Oxygen Prediction With Tree Tuned Deep Neural Network. IEEE Access 2020, 8, 182431–182440. [Google Scholar] [CrossRef]
- Liu, J.; Yu, C.; Hu, Z.; Zhao, Y.; Bai, Y.; Xie, M.; Luo, J. Accurate Prediction Scheme of Water Quality in Smart Mariculture with Deep Bi-S-SRU Learning Network. IEEE Access 2020, 8, 24784–24798. [Google Scholar] [CrossRef]
- Bilali, A.; Taleb, A.; Nafii, A.; Alabjah, B.; Mazigh, N. Prediction of sodium adsorption ratio and chloride concentration in a coastal aquifer under seawater intrusion using machine learning models. Environ. Technol. Innov. 2021, 23, 101641. [Google Scholar] [CrossRef]
- Jiang, J.; Zhou, H.; Zhang, T.; Yao, C.; Du, D.; Zhao, L.; Cai, W.; Che, L.; Cao, Z.; Wu, X.E. Machine learning to predict dynamic changes of pathogenic Vibrio spp. abundance on microplastics in marine environment. Environ. Pollut. 2022, 305, 119257. [Google Scholar] [CrossRef] [PubMed]
- Kim, H.-R.; Soh, H.Y.; Kwak, M.-T.; Han, S.-H. Machine Learning and Multiple Imputation Approach to Predict Chlorophyll-a Concentration in the Coastal Zone of Korea. Water 2022, 14, 1862. [Google Scholar] [CrossRef]
- Aydın Er, B.; Odabas, M.S.; Şenyer, N.; Ardali, Y. Evaluation of Deep Sea Discharge Systems Efficiency in the Eastern Black Sea Using Artificial Neural Network: A Case Study for Trabzon, Turkey. Braz. Arch. Biol. Technol. 2022, 65, e22210397. [Google Scholar]
- Xiao, C.; Chen, N.; Hu, C.; Wang, K.; Gong, J.; Cheng, Z. Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM- AdaBoost combination approach. Remote Sens. Environ. 2019, 233, 111358. [Google Scholar] [CrossRef]
- Hu, Z.; Zhang, Y.; Zhao, Y.; Xie, M.; Zhong, J.; Tu, Z.; Liu, J. A Water Quality Prediction Method Based on the Deep LSTM Network Considering Correlation in Smart Mariculture. Sensors 2019, 19, 1420. [Google Scholar] [CrossRef] [Green Version]
- Xiao, C.; Chen, N.; Hu, C.; Wang, K.; Xu, Z.; Cai, Y.; Xu, L.; Chen, Z.; Gong, J. A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data. Environ. Model. Softw. 2019, 120, 104502. [Google Scholar] [CrossRef]
- Han, M.; Feng, Y.; Zhao, X.; Sun, C.; Hong, F.; Liu, C. A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean. IEEE Access 2019, 7, 172816–172829. [Google Scholar] [CrossRef]
- Xie, J.; Zhang, J.; Yu, J.; Xu, L. An Adaptive Scale Sea Surface Temperature Predicting Method Based on Deep Learning with Attention Mechanism. IEEE Geosci. Remote Sens. Lett. 2020, 17, 740–744. [Google Scholar] [CrossRef]
- Liu, Y.; Zhang, Q.; Song, L.; Chen, Y. Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction. Comput. Electron. Agric. 2019, 165, 104964. [Google Scholar] [CrossRef]
- Zhao, J.; Mao, X.; Chen, L. Learning deep features to recognize speech emotion using merged deep CNN. IET Electr. Power Appl. 2018, 12, 713–721. [Google Scholar]
- Zhang, K.; Geng, X.; Yan, X. Prediction of 3-D Ocean Temperature by Multilayer Convolutional LSTM. IEEE Geosci. Remote Sens. Lett. 2020, 17, 1303–1307. [Google Scholar] [CrossRef]
Models | Model of Hidden Units | RMSE | MAPE | R2 |
---|---|---|---|---|
PCA–EEMD–CNN–Attention–GED (GRU Encoder-Decoder) | 16 | 0.821 | 0.564 | 92.67 |
64 | 0.778 | 0.549 | 93.36 | |
100 | 0.644 | 0.516 | 94.25 | |
200 | 0.694 | 0.540 | 93.92 |
Indicators | Component 1 | Component 2 | Component 3 | Component 4 | Component 5 |
---|---|---|---|---|---|
pH | −0.395 | 0.813 | 0.217 | −0.011 | 0.027 |
Turbidity | −0.636 | 0.172 | −0.255 | 0.222 | 0.247 |
Dissolved oxygen | 0.443 | 0.461 | 0.882 | 0.011 | −0.076 |
Water temperature | −0.768 | −0.325 | 0.471 | 0.148 | 0.078 |
Electrical conductivity | 0.571 | 0.219 | 0.092 | 0.687 | 0.232 |
Chemical oxygen demand | 0.809 | −0.094 | 0.253 | 0.184 | −0.197 |
Ammonia nitrogen | −0.358 | −0.079 | 0.873 | −0.169 | 0.515 |
Total phosphorus | 0.067 | 0.893 | 0.522 | −0.294 | 0.149 |
Potassium permanganate | 0.423 | −0.347 | −0.319 | −0.421 | 0.586 |
Redox potential | −0.256 | 0.210 | −0.734 | −0.164 | −0.415 |
Eigenvalue | 2.934 | 2.429 | 2.194 | 0.894 | 0.748 |
Contribution rate/% | 26.7 | 48.8 | 67.5 | 74.7 | 83.3 |
Models | In-Out | RMSE | MAPE | R2 (%) |
---|---|---|---|---|
PCA–EEMD–CNN–Attention–GED | 1-1 | 0.246 | 0.307 | 97.80 |
7-7 | 0.692 | 0.560 | 94.23 | |
15-15 | 0.832 | 0.596 | 93.57 | |
PCA–EEMD–CNN–Attention–LSTM | 1-1 | 0.347 | 0.347 | 96.94 |
7-7 | 0.834 | 0.605 | 93.48 | |
15-15 | 0.896 | 0.623 | 92.85 | |
PCA–EEMD–CNN–GED | 1-1 | 0.338 | 0.353 | 97.07 |
7-7 | 0.843 | 0.622 | 93.53 | |
15-15 | 1.021 | 0.642 | 91.89 | |
PCA–EEMD–GED | 1-1 | 0.345 | 0.362 | 96.91 |
7-7 | 0.757 | 0.548 | 93.20 | |
15-15 | 1.213 | 0.744 | 91.46 | |
CNN–Attention–GED | 1-1 | 0.394 | 0.418 | 96.46 |
7-7 | 0.747 | 0.563 | 93.68 | |
15-15 | 0.975 | 0.637 | 91.65 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xie, Z.; Li, Z.; Mo, C.; Wang, J. A PCA–EEMD–CNN–Attention–GRU–Encoder–Decoder Accurate Prediction Model for Key Parameters of Seawater Quality in Zhanjiang Bay. Materials 2022, 15, 5200. https://doi.org/10.3390/ma15155200
Xie Z, Li Z, Mo C, Wang J. A PCA–EEMD–CNN–Attention–GRU–Encoder–Decoder Accurate Prediction Model for Key Parameters of Seawater Quality in Zhanjiang Bay. Materials. 2022; 15(15):5200. https://doi.org/10.3390/ma15155200
Chicago/Turabian StyleXie, Zaimi, Zhenhua Li, Chunmei Mo, and Ji Wang. 2022. "A PCA–EEMD–CNN–Attention–GRU–Encoder–Decoder Accurate Prediction Model for Key Parameters of Seawater Quality in Zhanjiang Bay" Materials 15, no. 15: 5200. https://doi.org/10.3390/ma15155200