Water Quality Prediction Method Based on IGRA and LSTM

Abstract

Water quality prediction has great significance for water environment protection. A water quality prediction method based on the Improved Grey Relational Analysis (IGRA) algorithm and a Long-Short Term Memory (LSTM) neural network is proposed in this paper. Firstly, considering the multivariate correlation of water quality information, IGRA, in terms of similarity and proximity, is proposed to make feature selection for water quality information. Secondly, considering the time sequence of water quality information, the water quality prediction model based on LSTM, whose inputs are the features obtained by IGRA, is established. Finally, the proposed method is applied in two actual water quality datasets: Tai Lake and Victoria Bay. Experimental results demonstrate that the proposed method can take full advantage of the multivariate correlations and time sequence of water quality information to achieve better performance on water quality prediction compared with the single feature or non-sequential prediction methods.

Recent Advances in Information and Communications Technology (ICT) and Sensor Technology for Monitoring Water Quality

“…Thus, the recent development of these high technologies regarding field monitoring, data transmission, and analyses promotes the optimization of water quality management. However, many parts of water quality monitoring systems still rely on regular-basis manual sample collection and monitoring even though the collected data are analyzed by novel machine learning techniques [16,134,137,140]. Thus, it is essential to develop and apply in situ real-time monitoring systems using sensor technologies, along with high-tech data analysis techniques, such as deep learning, to find better solutions in water quality management.…”

“…However, this type possesses a more complex structure than RNNs for controlling the use of the previous memory in recurrent loops [149]. The LSTMs are increasingly employed in the analysis of water quality data sequencing [16,18,150]. Muharemi et al (2019) used various machine learning models (e.g., ANNs, SVMs, and LSTMs) for the analysis of time series data and suggested machine learning for the detection of anomalies in the water quality [142].…”

“…The general function of real-time online water quality monitoring systems is to conduct data acquisition, transmission, and interpretation of the measured data [2]. The advanced data analysis technologies, such as machine learning, also provide valuable tools for effective water quality data management (e.g., prediction of water quality changes) [16][17][18]. Recently, deep-learning, a type of machine learning method, is increasingly used for the analysis of massive environmental data, to provide useful information for water quality management.…”

Application of a Parallel Particle Swarm Optimization-Long Short Term Memory Model to Improve Water Quality Data

“…Appropriately chosen evaluation criteria are essential for assessing model performance. Because Krause has found that no single efficiency criterion can provide a full description of model performance [4] and each available criterion has certain benefits and drawbacks, we chose to apply two criteria: the MAE and the RMSE [6].…”

“…These networks have been successfully applied in the field of water time series prediction. For example, Jian Zhou used an LSTM network to predict dissolved oxygen [6] and Chen Liang used an LSTM network to predict the Dongting Lake water level variation [7]. However, the prediction accuracy of the LSTM algorithm used in these studies is influenced by the parameter selection.…”