A Review of Different Predictive Models for Water Pollution Problems
School of Machinery and Transportation, Southwest Forestry University, Kunming 650224, China
| Abstract: | Starting from the current water pollution problem, this paper describes the seriousness of the current water pollution problem as well as its harm, and explains the importance of constructing a water quality prediction model that matches the pollution problem. And then analyzed the main sources of data errors in the construction of prediction models. Since the water pollution problems in different basins have different degrees of differences, this paper proposes three prediction models that have been researched more than others, namely, BP neural network prediction model, LSTM (Long Short Memory Artificial Neural Network) prediction model, Random Forest Algorithm prediction model, and elaborates on the advantages and the current development status of each model and compares them with each other and explains the scope of water quality prediction model applicable to each model. The scope of each model is clarified. It shows that water quality prediction model has an important role in monitoring water quality, different water pollution basins matching water quality prediction model is not the same, a combination of multiple algorithms with each other to derive the prediction model may have a better prediction effect, and finally puts forward the prospect of water quality prediction modeling in the application of water pollution problems. |
| Keywords: | Water Pollution; Neural Networks; Water Quality Prediction Models; Algorithms |
| DOI: | 10.57237/j.res.2024.03.001 |
View:
Downloads:
Received: 12 June 2024
Accepted: 10 July 2024
Published Online: 18 July 2024
References
| [1] | Zeilhofer P, Zeilhofer L V A C, Hardoim E L, et al. GIS applications for mapping and spatial modeling of urban-use water quality: a case study in District of Cuiabá, Mato Grosso, Brazil [J]. Cadernos de saude publica, 2007, 23(4): 875-884. |
| [2] | Aldhyani T H H, Al-Yaari M, Alkahtani H, et al. Research Article Water Quality Prediction Using Artificial Intelligence Algorithms [J]. 2020. |
| [3] | Farrell-Poe K, Payne W, Emanuel R. Water Quality & Monitoring, University of Arizona Repository, 2000 [J]. |
| [4] | T. Taskaya-Temizel and M. C. Casey, “A comparative study of autoregressive neural network hybrids,” Neural Networks, vol. 18, no. 5–6, pp. 781–789, 2005. |
| [5] | Babu C N, Reddy B E. A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data [J]. Applied Soft Computing, 2014, 23: 27-38. |
| [6] | M. M. S. Cabral Pinto, C. M. Ordens, M. T. Condesso de Meloet al., “An inter-disciplinary approach to evaluate human health risks due to long-term exposure to contaminated groundwater near a chemical complex,” Exposure and Health, vol. 12, no. 2, pp. 199–214, 2020. |
| [7] | Cabral Pinto M M S, Marinho-Reis A P, Almeida A, et al. Human predisposition to cognitive impairment and its relation with environmental exposure to potentially toxic elements [J]. Environmental Geochemistry and Health, 2018, 40: 1767-1784. |
| [8] | Daigger G T. A practitioner’s perspective on the uses and future developments for wastewater treatment modelling [J]. Water Science and Technology, 2011, 63(3): 516-526. |
| [9] | 汪锐, 余雅丹, 潘志成, 等. 模拟预测模型在污水处理中的应用: 现状与挑战 [J]. 水处理技术, 2022, 48(06): 20-23+29. https://doi.org/10.16796/j.cnki.1000-3770.2022.06.004. |
| [10] | 陆超, 张峻, 赵俊. 基于神经网络的污水处理厂水质预测模型 [J]. 净水技术, 2013, 32(4): 100-105. |
| [11] | 连晓峰, 李晓婷, 潘峰. 机理模型与补偿模型相结合的污水处理工艺出水指标软测量预测模型研究 [J]. 计算机与应用化学, 2013, 30(10): 1143-1147. |
| [12] | 邹可可, 李中原, 穆小玲. 基于 LSTM GRU 的污水水质预测模型研究 [J]. 能源与环保, 2021, 43(12): 59. |
| [13] | 姚怡帆, 荆玉姝, 王丽艳, 等. 基于集成模型的污水处理厂出水总氮预测方法 [J]. 工业水处理, 2023, 43(09): 187-194. https://doi.org/10.19965/j.cnki.iwt.2022-1036. |
| [14] | 史鹏涛, 王璟德, 王健红. 基于混合模型的污水处理过程建模的研究 [J]. 计算机仿真, 2020, 37(08): 188-191+408. |
| [15] | 应用研究综述 [J]. 应用生态学报, 2013, 24(10): 3012-3018. https://doi.org/10.13287/j.1001-9332.2013.0479. |
| [16] | 陈鼎豪, 郑文丽, 王骥, 等. 简化一维水质模型在突发水污染事故模拟预测中的应用 [J]. 环境工程学报, 2021, 15(10): 3199-3203. |
| [17] | 史斌. 水污染动态预警监测模型构建与应急处置工程风险分析 [D]. 哈尔滨工业大学, 2018. |
| [18] | 王腾, 熊仲华, 杜庆治, 等. 基于马尔可夫链的河流水质污染预测模型研究 [J]. 安徽农业科学, 2015, 43(27): 209-211. https://doi.org/10.13989/j.cnki.0517-6611.2015.27.076. |
| [19] | Xu X, Lai T, Jahan S, et al. A machine learning predictive model to detect water quality and pollution [J]. Future Internet, 2022, 14(11): 324. |
| [20] | Rode M, Suhr U. Uncertainties in selected river water quality data [J]. Hydrology and Earth System Sciences, 2007, 11(2): 863-874. |
| [21] | Illingworth J A. A common source of error in pH measurements [J]. Biochemical Journal, 1981, 195(1): 259-262. |
| [22] | Patil A, Deng Z Q. Input data measurement-induced uncertainty in watershed modeling [J]. Hydrological sciences journal, 2012, 57(1): 118-133. |
| [23] | Camargos C, Julich S, Houska T, et al. Effects of input data content on the uncertainty of simulating water resources [J]. Water, 2018, 10(5): 621. |
| [24] | Wu X, Marshall L, Sharma A. Quantifying input uncertainty in the calibration of water quality models: reshuffling errors via the secant method [J]. Hydrology and Earth System Sciences Discussions, 2020, 2020: 1-26. |
| [25] | Yuan L L. Effects of measurement error on inferences of environmental conditions [J]. Journal of the North American Benthological Society, 2007, 26(1): 152-163. |
| [26] | 马丰魁, 姜群鸥, 徐藜丹, 等. 基于 BP 神经网络算法的密云水库水质参数反演研究 [J]. 生态环境学报, 2020, 29(3): 569. |
| [27] | 高峰, 冯民权, 滕素芬. 基于 PSO 优化 BP 神经网络的水质预测研究 [J]. 安全与环境学报, 2015, 15(4): 338-341. |
| [28] | 李海涛, 王博睿. 基于粒子群算法优化的 BP 神经网络在海水水质评价中的应用 [J]. 海洋科学, 2020, 44(6): 31-36. |
| [29] | 张青, 王学雷, 张婷, 等. 基于 BP 神经网络的洪湖水质指标预测研究 [J]. 湿地科学, 2016, 14(2): 212-218. |
| [30] | 郭庆春, 郝源, 李雪, 等. BP 神经网络在长江水质 COD 预测中的应用 [J]. 计算机技术与发展, 2014, 24(4): 235-238. |
| [31] | 纪广月.基于改进粒子群算法优化BP神经网络的西江水质预测研究 [J]. 水动力学研究与进展 (A辑), 2020, 35(05): 567-574. https://doi.org/10.16076/j.cnki.cjhd.2020.05.003. |
| [32] | 华祖林, 钱蔚, 顾莉. 改进型 LM-BP 神经网络在水质评价中的应用 [J]. 水资源保护, 2008, 24(4): 22-25. |
| [33] | 王李, 刘志斌, 常欢. 自适应遗传 BP 神经网络在水质预测中应用 [J]. 微计算机信息, 2011, 27(4): 230-231. |
| [34] | Xu M, Zeng G, Xu X, et al. Application of Bayesian regularized BP neural network model for analysis of aquatic ecological data–a case study of chlorophyll-a prediction in Nanzui water area of Dongting Lake [J]. Journal of Environmental Sciences, 2005, 17(6): 946-952. |
| [35] | Gaume E, Gosset R. Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology? [J]. Hydrology and Earth System Sciences, 2003, 7(5): 693-706. |
| [36] | 刘国东, 丁晶. BP 网络用于水文预测的几个问题探讨 [J]. 水利学报, 1999 (1): 65-70. |
| [37] | Fernandes A, Chaves H, Lima R, et al. Draw on artificial neural networks to assess and predict water quality [C] // IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2020, 612(1): 012028. |
| [38] | 孙铭, 魏守科, 王莹洁, 等. 基于小波分解的 LSTM 水质预测模型 [J]. 计算机系统应用, 2020, 29(12): 55-63. |
| [39] | 李彦杰, 贺鹏飞, 冯巍巍, 等. 基于 LSTM 模型的海洋水质预测 [J]. 计算机与数字工程, 2020, 48(2): 437-441. |
| [40] | Gandh D R, Haq K P R A, Harigovindan V P, et al. LSTM and GRU based Accurate Water Quality Prediction for Smart Aquaculture [C] // Journal of Physics: Conference Series. IOP Publishing, 2023, 2466(1): 012027. |
| [41] | Liu Y, Liu P, Wang X, et al. A study on water quality prediction by a hybrid dual channel CNN-LSTM model with attention mechanism [C]//International Conference on Smart Transportation and City Engineering 2021. SPIE, 2021, 12050: 797-804. |
| [42] | Tao D, Yang Y, Cai Z, et al. Application of vmd-lstm in water quality prediction [C] // Journal of Physics: Conference Series. IOP Publishing, 2023, 2504(1): 012057. |
| [43] | Baek S S, Pyo J, Chun J A. Prediction of water level and water quality using a CNN-LSTM combined deep learning approach [J]. Water, 2020, 12(12): 3399. |
| [44] | Tian X, Wang Z, Taalab E, et al. Water quality predictions based on grey relation analysis enhanced LSTM algorithms [J]. Water, 2022, 14(23): 3851. |
| [45] | Tang S, Sun F, Liu W, et al. Optimal postprocessing strategies with LSTM for global streamflow prediction in ungauged basins [J]. Water Resources Research, 2023, 59(7): e2022WR034352. |
| [46] | 项新建, 许宏辉, 谢建立, 等. 基于 VMD-TCN-GRU 模型的水质预测研究 [J]. Yellow River, 2024, 46(3). |
| [47] | Wu X. Water quality prediction based on AR and LSTM model [C] // Journal of Physics: Conference Series. IOP Publishing, 2023, 2580(1): 012019. |
| [48] | 郝玉莹, 赵林, 孙同, 等. 基于 RF-LSTM 的地表水体水质预测 [J]. 水资源与水工程学报, 2021, 32(6): 41-48. |
| [49] | 闫佰忠, 孙剑, 安娜. 基于随机森林模型的地下水水质评价方法 [J]. 水电能源科学, 2019, 37(11): 66-69. |
| [50] | 胡悦, 范小娟. 基于随机森林算法的河南地区地表水水质预测与评价 [J]. 广东水利水电, 2023, (07): 81-85. |
| [51] | 王涌, 陆卫, 左楚涵, 等.基于改进随机森林模型的水质BOD快速预测研究 [J]. 传感技术学报, 2021, 34(11): 1482-1488. |
| [52] | 王雪. 基于随机森林算法的唐山市水质评价 [J]. 水利技术监督, 2018, (05): 173-176. |
| [53] | 王盼, 陆宝宏, 张瀚文, 等. 基于随机森林模型的需水预测模型及其应用 [J]. 水资源保护, 2014, 30(1): 34-37. |
| [54] | Xu J, Xu Z, Kuang J, et al. An alternative to laboratory testing: Random forest-based water quality prediction framework for inland and nearshore water bodies [J]. Water, 2021, 13(22): 3262. |
| [55] | 谷志新, 郭宇. 基于混合集成学习算法的香港林村河水质指标预测 [J]. 水电能源科学, 2022. |
| [56] | Smoliński S. Incorporation of optimal environmental signals in the prediction of fish recruitment using random forest algorithms [J]. Canadian journal of fisheries and aquatic sciences, 2019, 76(1): 15-27. |
| [57] | Dong J, Wang Z, Wu J, et al. A water quality prediction model based on signal decomposition and ensemble deep learning techniques [J]. Water Science & Technology, 2023, 88(10): 2611-2632. |
| [58] | 张颖, 高倩倩. 基于随机森林分类算法的巢湖水质评价 [J]. 环境工程学报, 2016, 10(02): 992-998. |
| [59] | 辛辰, 刘鸿斌. 预测造纸废水出水指标的随机森林建模方法 [J]. 中国造纸, 2019, 38(08): 57-62. |
Join the Editorial Board
We invite active, qualified and high profile scientists and researchers to join as Editorial Board Members.
Join UsBecome a Reviewer
Scholars with a strong interest in reviewing are invited to join the reviewer panel to ensure the quality of the research to be published.
Join Us