Application of LSTM Model Combining Improved Fruit-Fly Algorithm after Seasonal-Trend Decomposition using LOESS to Water Quality Prediction

GUO Li-jin; XU Rui-wei

doi:10.11988/ckyyb.20220242

PDF(5953 KB)

Journal of Changjiang River Scientific Research Institute ›› 2023, Vol. 40 ›› Issue (8) : 57-63. DOI: 10.11988/ckyyb.20220242

Water Environment and Water Ecology

Application of LSTM Model Combining Improved Fruit-Fly Algorithm after Seasonal-Trend Decomposition using LOESS to Water Quality Prediction

GUO Li-jin^1,2, XU Rui-wei^1,2

Author information +

History +

Abstract

Real-time variations in water quality environment and the internal coupling pose challenges to predicting water quality efficiently and accurately. To extract further information from the time series data and enhance the accuracy of prediction models, we propose a novel combined prediction model for Dissolved Oxygen (DO). To begin with, the water quality data is decomposed using the Seasonal and Trend decomposition using LOESS (STL) technique. Subsequently, the obtained seasonal component, trend component, and residual component are fed into the Long Short-Term Memory network model (LSTM) for prediction. In order to address the impact of LSTM network initialization parameters on prediction performance, we introduce an optimization approach based on the Fruit fly algorithm utilizing Gaussian function. Finally, the predicted values of each component are reconstructed to the DO prediction values. To validate the effectiveness of the proposed model, we conduct simulation tests utilizing water quality data from three sections of Haihe River. Results demonstrate that the combined model exhibits a favorable prediction effect on the DO concentration of the three stations, characterized by minimal errors and strong generalizability.

Key words

water quality prediction / STL / fruit-fly algorithm / LSTM / dissolved oxygen

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

GUO Li-jin, XU Rui-wei. Application of LSTM Model Combining Improved Fruit-Fly Algorithm after Seasonal-Trend Decomposition using LOESS to Water Quality Prediction[J]. Journal of Changjiang River Scientific Research Institute. 2023, 40(8): 57-63 https://doi.org/10.11988/ckyyb.20220242

References

[1] 刘永, 蒋青松, 梁中耀, 等. 湖泊富营养化响应与流域优化调控决策的模型研究进展[J]. 湖泊科学, 2021, 33(1): 49-63.
[2] 马景, 武周虎, 邹艳均, 等. 基于灰色马尔科夫模型的南四湖水质预测[J]. 水资源保护, 2021, 37(5): 153-158.
[3] 石子泊, 邹志红. 基于小波变换的ARIMA模型在水质预测中的应用研究[J]. 环境工程学报, 2014, 8(10): 4550-4554.
[4] 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.
[5] KHAN U T, VALEO C. A New Fuzzy Linear Regression Approach for Dissolved Oxygen Prediction[J]. Hydrological Sciences Journal, 2015, 60(6): 1096-1119.
[6] 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.
[7] 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.
[8] 孟海宁, 童新宇, 石月开, 等. 基于ARIMA-RNN组合模型的云服务器老化预测方法[J]. 通信学报, 2021, 42(1): 163-171.
[9] HOCHREITERS,SCHMIDHUBER J.Long Short-Term Memory[J].Neural Computation,1997,9(8):1735-1780.
[10] 王嫄嫄. 基于LSTM的水质预测方法研究[D]. 南京: 南京邮电大学, 2019.
[11] 秦文虎,陈溪莹.基于长短时记忆网络的水质预测模型研究[J].安全与环境学报,2020,20(1):328-334.
[12] ZHOU J, WANG Y, XIAO F, et al. Water Quality Prediction Method Based on IGRA and LSTM[J]. Water, 2018, 10(9): 1148.
[13] 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.
[14] 宋刚, 张云峰, 包芳勋, 等. 基于粒子群优化LSTM的股票预测模型[J]. 北京航空航天大学学报, 2019, 45(12): 2533-2542.
[15] 薛晗, 邵哲平, 潘家财, 等. 基于文化萤火虫算法-广义回归神经网络的船舶交通流量预测[J]. 上海交通大学学报, 2020, 54(4): 421-429.
[16] 任燕龙, 谷建伟, 崔文富, 等. 基于改进果蝇算法和长短期记忆神经网络的油田产量预测模型[J]. 科学技术与工程, 2020, 20(18): 7245-7251.
[17] ROJO J, RIVERO R, ROMERO-MORTE J, et al. Modeling Pollen Time Series Using Seasonal-Trend Decomposition Procedure Based on LOESS Smoothing[J]. International Journal of Biometeorology, 2017, 61(2): 335-348.
[18] ALIZADEH M J, KAVIANPOUR M R. Development of Wavelet-ANN Models to Predict Water Quality Parameters in Hilo Bay, Pacific Ocean[J]. Marine Pollution Bulletin, 2015, 98(1/2): 171-178.
[19]贺琪, 查铖, 宋巍, 等. 基于STL的海表面温度预测算法[J]. 海洋环境科学, 2020, 39(6): 918-925.
[20] 陈英义, 方晓敏, 梅思远, 等. 基于WT-CNN-LSTM的溶解氧含量预测模型[J]. 农业机械学报, 2020, 51(10): 284-291.
[21] 马杰. 基于季节指数与Adam优化的LSTM短期电力负荷预测研究[D]. 北京: 北京工业大学, 2020.
[22] 潘文超.果蝇最佳化演算法:最新演化式计算技术[M]. 台中: 沧海书局, 2011:10-12.
[23] 宁剑平,王冰,李洪儒,等.递减步长果蝇优化算法及应用[J].深圳大学学报(理工版),2014,31(4):367-373.
[24] 徐江, 李艳, 纪晶华. 统计学基础[M]. 2版. 北京: 机械工业出版社, 2015: 33-58.