At present, due to the eutrophication of the water body itself and the man-made discharge of pollutants, the large and small water bodies in many areas have been polluted, which is the main reason for the surface water pollution and soil erosion caused by over-exploitation of land in many areas. In many economically backward areas, low productivity, chemical fertilizer pollution or soil erosion can nourish water. To control reservoir pollution, it is necessary to consider the current emission level of indicators and point sources. In this paper, the Deep Learning (DL) algorithm was used to optimize the reservoir pollution control engineering system. This paper calculated the contribution value of each Pollution Source (PS) according to the classification of reservoir PS. On the basis of the contribution value of each PS, the DL algorithm was used to predict water quality pollution, and the water environment capacity model was established according to the pollution load prediction of the reservoir basin. The combination of water quality pollution prediction and water environment capacity model could monitor the reservoir pollution and control the water pollution in time. The experimental part studied the prediction effect of water pollution. The experimental results showed that the DL prediction algorithm had good water quality prediction ability. The error of reservoir pH (hydrogen ion concentration index) was less than 0.5, and the prediction error of COD (Chemical Oxygen Demand) content in water was less than 10%.

Xiangdong Ma. System Optimization of Reservoir Pollution Prevention and Control Engineering under Deep Learning. Water Pollution Prevention and Control Project (2021), Vol. 2, Issue 4: 22-31. https://doi.org/10.38007/WPPCP.2021.020403.

[1] Wikurendra Edza Aria. Water quality analysis of pucang river, sidoarjo regency to control water pollution. Environmental Quality Management. (2021) 32(1): 133-144. https://doi.org/10.1002/tqem.21855

[2] Mingjing He. Waste-derived biochar for water pollution control and sustainable development. Nature Reviews Earth & Environment. (2021) 3(7): 444-460. 

[3] Li Zhou, Lingzhi Li, Jikun Huang. The river chief system and agricultural non-point source water pollution control in China. Journal of Integrative Agriculture. (2021) 20(5): 1382-1395. https://doi.org/10.1016/S2095-3119(20)63370-6

[4] Long Bui Ta. Inverse algorithm for Streeter-Phelps equation in water pollution control problem. Mathematics and Computers in Simulation. (2020) 171(5): 119-126. https://doi.org/10.1016/j.matcom.2019.12.005

[5] Xiang Li. Research Progress on the Application of Magnetic Nanomaterials in Water Pollution Control. Mini-Reviews in Organic Chemistry. (2021) 20(3): 240-249. https://doi.org/10.2174/1570193X19666220328162619

[6] Martini Sri. Membrane technology for water pollution control: a review of recent hybrid mechanism. Jurnal Rekayasa Kimia & Lingkungan. (2021) 17(1): 83-96. https://doi.org/10.23955/rkl.v17i1.23610

[7] Sit Muhammed. A comprehensive review of deep learning applications in hydrology and water resources. Water Science and Technology. (2020) 82(12): 2635-2670. https://doi.org/10.2166/wst.2020.369

[8] Barzegar Rahim, Mohammad Taghi Aalami, Jan Adamowski. Short-term water quality variable prediction using a hybrid CNN-LSTM deep learning model. Stochastic Environmental Research and Risk Assessment. (2020) 34(2): 415-433. https://doi.org/10.1007/s00477-020-01776-2

[9] Han Zhang. Evaluating water resource carrying capacity using the deep learning method: a case study of Yunnan, Southwest China. Environmental Science and Pollution Research. (2021) 29(32): 48812-48826. 

[10] Read Jordan S. Process-guided deep learning predictions of lake water temperature. Water Resources Research. (2019) 55(11): 9173-9190. https://doi.org/10.1029/2019WR024922

[11] Venkataramana Y. Water quality analysis in a lake using deep learning methodology: prediction and validation. International Journal of Environmental and Analytical Chemistry. (2021) 102(17): 5641-5656. https://doi.org/10.1080/03067319.2020.1801665

[12] Khullar Sakshi, Nanhey Singh. Water quality assessment of a river using deep learning Bi-LSTM methodology: forecasting and validation. Environmental Science and Pollution Research. (2021) 29(9): 12875-12889. https://doi.org/10.1007/s11356-021-13875-w

[13] Herath Imali Kaushalya. Heavy metal toxicity, ecological risk assessment, and pollution sources in a hydropower reservoir. Environmental Science and Pollution Research. (2021) 29(22): 32929-32946. 

[14] Yuwei Huang. Iron-activated carbon systems to enhance aboriginal aerobic denitrifying bacterial consortium for improved treatment of micro-polluted reservoir water: performances, mechanisms, and implications. Environmental Science & Technology. (2021) 56(6): 3407-3418. https://doi.org/10.1021/acs.est.1c05254

[15] Saha Ajoy. Phosphorus fractions in the sediment of a tropical reservoir, India: implications for pollution source identification and eutrophication. Environmental Geochemistry and Health. (2021) 44(3): 749-769. https://doi.org/10.1007/s10653-021-00985-0