FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework

Water quality prediction plays a crucial role in both enterprise management and government environmental management. However, due to the variety in water quality data, inconsistent frequency of data acquisition, inconsistency in data organization, and volatility and sparsity of data, predicting water quality accurately and efficiently has become a key problem. This paper presents a recurrent neural network water quality prediction method based on a sequence-to-sequence (seq2seq) framework. The gate recurrent unit (GRU) model is used as an encoder and decoder, and a factorization machine (FM) is integrated into the model to solve the problem of high sparsity and high dimensional feature interaction in the data, which was not addressed by the water quality prediction models in prior research. Moreover, due to the long period and timespan of water quality data, we add a dual attention mechanism to the seq2seq framework to address memory failures in deep learning. We conducted a series of experiments, and the results show that our proposed method is more accurate than several typical water quality prediction methods.

[1]  J. Adamowski,et al.  Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model , 2020, Stochastic Environmental Research and Risk Assessment.

[2]  Sheau-Ling Hsieh,et al.  Artificial Intelligence Methodologies Applied to Prompt Pluvial Flood Estimation and Prediction , 2020, Water.

[3]  Ching-Hsue Cheng,et al.  A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method , 2017, Comput. Intell. Neurosci..

[4]  Reza Malekian,et al.  An Improved LSSVM Model for Intelligent Prediction of the Daily Water Level , 2018, Energies.

[5]  J. Chun,et al.  Prediction of Water Level and Water Quality Using a CNN-LSTM Combined Deep Learning Approach , 2020 .

[6]  Weinan Zhang,et al.  User Behavior Retrieval for Click-Through Rate Prediction , 2020, SIGIR.

[7]  Chi-Hua Chen,et al.  Water Level Prediction Model Based on GRU and CNN , 2020, IEEE Access.

[8]  J. Kadane.  Structural Analysis of Discrete Data with Econometric Applications , 1984 .

[9]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[10]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[11]  F. Pacheco,et al.  A Method for Estimating the Risk of Dam Reservoir Silting in Fire-Prone Watersheds: A Study in Douro River, Portugal , 2020, Water.

[12]  Yifan Wu,et al.  A Novel Wind Speed Interval Prediction Based on Error Prediction Method , 2020, IEEE Transactions on Industrial Informatics.

[13]  Li Tianliang,et al.  Prediction and analysis of chaotic time series on the basis of support vector , 2008 .

[14]  Zibin Zheng,et al.  Web Service Personalized Quality of Service Prediction via Reputation-Based Matrix Factorization , 2016, IEEE Transactions on Reliability.

[15]  Maziar Palhang,et al.  Generalization performance of support vector machines and neural networks in runoff modeling , 2009, Expert Syst. Appl..

[16]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[17]  A Forecasting Method for Harmful Algal Bloom(HAB)-Prone Regions Allowing Preemptive Countermeasures Based only on Acoustic Doppler Current Profiler Measurements in a Large River , 2020 .

[18]  Carlos Alberto Villacorta Cardoso,et al.  Forecasting Natural Gas Consumption using ARIMA Models and Artificial Neural Networks , 2016 .

[19]  Shahaboddin Shamshirband,et al.  Prediction of Water-Level in the Urmia Lake Using the Extreme Learning Machine Approach , 2016, Water Resources Management.

[20]  Jianmin Gao,et al.  A dilated convolution network-based LSTM model for multi-step prediction of chaotic time series , 2019, Computational and Applied Mathematics.

[21]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[22]  Chengfu Huo,et al.  Deep Match to Rank Model for Personalized Click-Through Rate Prediction , 2020, AAAI.

[23]  E. Jaynes.  On the rationale of maximum-entropy methods , 1982, Proceedings of the IEEE.

[24]  Alexander L. Wolf,et al.  A conceptual basis for feature engineering , 1999, J. Syst. Softw..