人工神经网络在地下水水质预测中的研究进展

Research progress on artificial neural network in groundwater quality prediction

摘要

介绍了人工神经网络(artificial neural network, ANN)在地下水水质预测中的应用原理、应用现状,以及优化神经网络的常用算法和模型.同时,针对目前人工神经网络在地下水水质预测中出现的问题,对未来可能的研究方向进行了展望,以期为地下水管理提供参考依据.

Abstract

This paper introduces the application principles and current status of artificial neural network (ANN) in groundwater quality prediction, as well as common algorithms and models for optimizing neural networks. At the same time, in response to the existing issues in the application of ANN for groundwater quality prediction, potential future research directions are discussed to provide references for groundwater management.

关键词

人工神经网络 / 水质预测模型 / 机理性模型 / 非机理性模型

Key words

artificial neural network / water quality prediction model / mechanistic model / non-mechanistic model

参考文献

[1] 张娇林. 地下水污染环境评价探讨[J]. 清洗世界, 2023, 39(5): 113-115.

[2] 郭庆春. 基于神经网络的大气污染预测[J]. 电子测试, 2015(18): 75-76.

[3] SAJADIAN A, HEIDARZADEH N. The effect of the gypsum formation on the water quality of reservoirs: a case study of Kosar dam basin, Iran[J]. Journal of Geochemical Exploration, 2022, 243: 107107.

[4] ALOUIS, MAZZONI A , ELOMRI A , et al. A review of Soil and Water Assessment Tool (SWAT) studies of Mediterranean catchments: applications, feasibility, and future directions[J]. Journal of Environmental Management, 2023, 326: 116799.

[5] GONELLA M, GAMBOLATI G, GIUNTA G, et al. Prediction of land subsidence due to groundwater withdrawal along the Emilia-Romagna coast[M]// GAMBOLATI G. CENAS. Dordrecht: Springer Netherlands, 1998: 151-168.

[6] MIRSANJARI M M, MOHAMMADYARI F. Application of time-series model to predict groundwater quality parameters for agriculture: Plain Mehran case study[C]// 2017 International Conference on Renewable Energy and Environment. [S. l.]: IOP Publishing, 2018, 127: 012012.

[7] 王渊. 灰色预测模型在邯郸市鸡泽县地下水矿化度的应用[D].邯郸:河北工程大学, 2018.

[8] KRHODA G O, AMIMO M O. Groundwater quality prediction using logistic regression model for Garissa County[J]. Africa Journal of Physical Sciences, 2019, 3: 13-27.

[9] SAKIZADEH M. Artificial intelligence for the prediction of water quality index in groundwater systems[J]. Modeling Earth Systems and Environment, 2016, 2: 1-9.

[10] HUANG X, GAO L, CROSBIE S, et al. Groundwater recharge prediction using linear regression, multi-layer perception network, and deep learning[J]. Water, 2019, 11(9): 1879.

[11] AL-MAHALLAWI K, MANIA J, HANIA A, et al. Using of neural networks for the prediction of nitrate groundwater contamination in rural and agricultural areas[J]. Environmental Earth Sciences, 2012, 65(3): 917-928.

[12] 肖燚, 郭亚会, 李明蔚, 等. 基于机器学习的地下水水质预测研究[J]. 北京师范大学学报(自然科学版), 2022, 58(2): 261-268.

[13] WANG M X, LIU G D, WU W L, et al. Prediction of agriculture derived groundwater nitrate distribution in North China Plain with GIS-based BPNN[J]. Environmental Geology, 2006, 50(5): 637-644.

[14] YAN Q, SONG Y, ZHOU W. Evaluation and predication of groundwater quality based on fuzzy model and BP neural networks[J]. Revista Técnica de la Facultad de Ingeniería de la Universidad del Zulia, 2016, 39(5): 340-350.

[15] TAŞAN M, TAŞAN S, DEMIR Y. Estimation and uncertainty analysis of groundwater quality parameters in a coastal aquifer under seawater intrusion: a comparative study of deep learning and classic machine learning methods[J]. Environmental Science and Pollution Research, 2023, 30(2): 2866-2890.

[16] RAMESH K B, VANITHA S. Exploring groundwater quality trends in Valliyar Sub-Basin, Kanniyakumari District, India through advanced machine learning Techniques[J]. Water, 2024, 16(11): 1531.

[17] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

[18] LIU P, WANG J, SANGAIAH A K, et al. Analysis and prediction of water quality using LSTM deep neural networks in IoT environment[J]. Sustainability, 2019, 11(7): 2058.

[19] ALFWZAN W F, SELIM M M, ALTHOBAITI S, et al. Application of Bi-LSTM method for groundwater quality assessment through water quality indices[J]. Journal of Water Process Engineering, 2023, 53: 103889.

[20] GORGIJAD, ASKARI G, TAGHIPOUR A A, et al. Spatiotemporal forecasting of the groundwater quality for irrigation purposes, using deep learning method: long short-term memory (LSTM)[J]. Agricultural Water Management, 2023, 277: 108088.

[21] KASISELVANATHAN M, SURESH A, SINDUJA M, et al. Prediction of groundwater quality in western regions of Tamilnadu using LSTM network[J]. Groundwater for Sustainable Development, 2024, 25: 101156.

[22] HU Z H, ZHANG Y R, ZHAO Y C, et al. A water quality prediction method based on the deep LSTM network considering correlation in smart mariculture[J]. Sensors, 2019, 19(6): 1420.

[23] WU J, LI Z B, ZHU L, et al. Optimized BP neural network for dissolved oxygen prediction[J]. IFAC-PapersOnLine, 2018, 51(17): 596-601.

[24] ALIZAMIR M, SOBHANARDANI S. An artificial neural network-particle swarm optimization (ANN-PSO) approach to predict heavy metals contamination in groundwater resources[J]. Jundishapur Journal of Health Sciences, 2018, 10(2): e67544.

[25] DING Y R, CAI Y J, SUN P D, et al. The use of combined neural networks and genetic algorithms for prediction of river water quality[J]. Journal of Applied Research and Technology, 2014, 12(3): 493-499.

[26] 司训练, 孔祥超. 石油开发背景下地下水水质预测研究[J]. 西安石油大学学报(社会科学版), 2020, 29(3): 53-59.

[27] BHAVYA R, SIVARAJ K, ELANGO L. Ant colony based artificial neural network for predicting spatial and temporal variation in groundwater quality[J]. Water, 2023, 15(12): 2222.

[28] 秦梓萱, 郭健, 许模. 基于ARIMA-BP模型的北京市平谷区地下水水质双尺度预测[J]. 兰州大学学报(自然科学版), 2023, 59(1): 121-128.

[29] 杨平, 王新民, 路来君. 基于改进的数量化理论和RBF神经网络组合方法的地下水水质预测[J]. 地学前缘, 2016, 23(3): 151-155.

[30] MAROUFPOOR S, JALALI M, NIKMEHR S, et al. Modeling groundwater quality by using hybrid intelligent and geostatistical methods[J]. Environmental Science and Pollution Research, 2020, 27(22): 28183-28197.

[31] VALADKHAN D, MOGHADDASI R, MOHAMMADINEJAD A. Groundwater quality prediction based on LSTM RNN: an Iranian experience[J]. International Journal of Environmental Science and Technology, 2022, 19(11): 11397-11408.

[32] ZHAO Y F, YANG L P, PAN H J, et al. Spatio-temporal prediction of groundwater vulnerability based on CNN-LSTM model with self-attention mechanism: a case study in Hetao Plain, northern China[J]. Journal of Environmental Sciences, 2025, 153: 128-142.