西丽水库是深圳重要饮水源之一,水库的水质影响着全市人民的供水安全。为及时准确预测西丽水库水质结果,以指导水库水厂供水计划的制定,在利用自适应噪声的完备集合经验模态分解方法进行数据分解的基础上,利用长短期记忆网络(LSTM)模型,建立了基于LSTM的西丽水库水质预测模型。通过模拟计算发现,模型模拟效果较好,其中水质预测模型中总氮、氨氮及总磷的预测结果与实测结果吻合度均较高,能够很好地模拟水库水质浓度变化过程;且对于总氮和氨氮,模型的相对预报误差能控制在10%以下,说明了所建模型的合理性。研究成果可为西丽水库的水质预测及供水计划的制定提供重要模型与技术支撑。
Abstract
Xili reservoir is one of the most important drinking water sources in Shenzhen. The water quality of the reservoir affects the water supply safety of the whole city. We aim to get timely and accurate water quality prediction results for formulating a scientific and reasonable water supply plan for the reservoir and water plant. Based on data decomposition using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), we established a long- and short-term memory network model of water quality prediction for Xili Reservoir. Through extensive simulation and calculation, the model demonstrates excellent performance. The prediction results of total nitrogen, ammonia nitrogen and total phosphorus in the water quality prediction model are in good agreement with measured results. For total nitrogen and ammonia nitrogen, the relative prediction error of the model can be controlled below 10%. This highlights the model’s ability to effectively simulate the changing water quality in the reservoir and underscores the model’s rationality. The research findings serve as vital model and technical support for water quality prediction and the development of water supply plans for the Xili Reservoir.
关键词
水质预测 /
神经网络 /
长短期记忆网络(LSTM) /
CEEMDAN分解 /
西丽水库
Key words
water quality prediction /
neural network /
long-short term memory(LSTM) /
CEEMDAN decomposition /
Xili Reservoir
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 孙 娜. 机器学习理论在径流智能预报中的应用研究[D]. 武汉: 华中科技大学, 2019.
[2] 张贻婷,李天宏. 基于长短时记忆神经网络的河流水质预测研究[J]. 环境科学与技术,2021,44(8):163-169.
[3] 李鑫鑫, 郑 丹, 杨建喜, 等. 基于GA-BP神经网络的施工区域水质预测及预警模型研究[J]. 重庆交通大学学报(自然科学版), 2020, 39(12): 106-110.
[4] KRATZERT F, KLOTZ D, SHALEV G, et al. Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine Learning Applied to Large-Sample Datasets[J]. Hydrology and Earth System Sciences, 2019, 23(12): 5089-5110.
[5] BEN TAIEB S, BONTEMPI G, ATIYA A F, et al. A Review and Comparison of Strategies for Multi-step Ahead Time Series Forecasting Based on the NN5 Forecasting Competition[J]. Expert Systems With Applications, 2012, 39(8): 7067-7083.
[6] XIANG Z, YAN J, DEMIR I. A Rainfall-Runoff Model with LSTM-Based Sequence-to-Sequence Learning[J]. Water Resources Research, 2020, doi: 10.1029/2019WR025326.
[7] 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.
[8] 顾乾晖, 曾 斌, 涂振宇. 基于VMD-PSO-LSTM水质预测模型的应用研究[J]. 南昌工程学院学报, 2021, 40(4): 23-29.
[9] 谷妙春. 基于噪声统计的EMD-LSTM网络流量预测方法[J]. 计算机测量与控制, 2023, 31(2): 21-27.
[10]白雯睿, 杨毅强, 郭 辉, 等. 基于VMD-CNN-LSTM的珠江流域水质多步预测模型研究[J]. 四川轻化工大学学报(自然科学版), 2022, 35(4): 66-74.
[11]刘雨薇. 基于VMD和改进LSTM的短期电力负荷预测研究[D]. 武汉: 湖北工业大学, 2020.
[12]梁 栋, 宗栋良. 深圳西丽水库水质研究[J]. 环境科学与技术, 2013, 36(增刊1): 315-318.
[13]宗栋良, 方俊峰, 王依林. 降雨及径流对西丽水库水质的影响[J]. 中国农村水利水电, 2006(2): 38-40.
[14]BUROVA A. Reducing the Error of Digital Algorithms for Deductive Signal Processing Based on Their Multi-Stage Discrete Fourier Transform by the Difference Digital Filters[C]∥2020 22th International Conference on Digital Signal Processing and its Applications (DSPA). March 25-27, 2020, Moscow, Russia. New York: IEEE Press, 2020: 1-3.
[15]石志炜, 张丽萍. 基于改进小波包阈值降噪的滚动轴承故障分析[J]. 计算机测量与控制, 2019, 27(5): 58-63.
[16]周 璇, 鲍长春, 夏丙寅. 融合统计模型与EMD的宽带话音增强方法[J]. 通信学报, 2013, 34(8): 95-101.
[17]周彦辰, 胡铁松, 陈 进, 等. 耦合动态方程的神经网络模型在水质预测中的应用[J]. 长江科学院院报, 2017, 34(9): 1-5.
[18]赵会茹, 张士营, 赵一航, 等. 基于自适应噪声完备经验模态分解-样本熵-长短期记忆神经网络和核密度估计的短期电力负荷区间预测[J]. 现代电力, 2021, 38(2): 138-146.
[19]刘俊威, 吕惠进. 人工神经网络在水质预测中的应用研究[J]. 长江科学院院报, 2012, 29(9): 95-97.
[20]罗学科, 何云霄, 刘 鹏, 等. ARIMA-SVR组合方法在水质预测中的应用[J]. 长江科学院院报, 2020, 37(10): 21-27.
PDF(1533 KB)
