scholarly journals A Long-Term Water Quality Prediction Method Based on the Temporal Convolutional Network in Smart Mariculture

Water ◽  
2021 ◽  
Vol 13 (20) ◽  
pp. 2907
Author(s):  
Yuexin Fu ◽  
Zhuhua Hu ◽  
Yaochi Zhao ◽  
Mengxing Huang
Keyword(s):  
Water Quality ◽  
Prediction Method ◽  
Quality Parameters ◽  
Quality Data ◽  
Convolutional Network ◽  
Water Quality Data ◽  
Water Quality Prediction ◽  
Term Prediction ◽  
Long Term Prediction

In smart mariculture, traditional methods are not only difficult to adapt to the complex, dynamic and changeable environment in open waters, but also have many problems, such as poor accuracy, high time complexity and poor long-term prediction. To solve these deficiencies, a new water quality prediction method based on TCN (temporal convolutional network) is proposed to predict dissolved oxygen, water temperature, and pH. The TCN prediction network can extract time series features and in-depth data features by introducing dilated causal convolution, and has a good effect of long-term prediction. At the same time, it is predicted that the network can process time series data in parallel, which greatly improves the time throughput of the model. Firstly, we arrange the 23,000 sets of water quality data collected in the cages according to time. Secondly, we use the Pearson correlation coefficient method to analyze the correlation information between water quality parameters. Finally, a long-term prediction model of water quality parameters based on a time domain convolutional network is constructed by using prior information and pre-processed water quality data. Experimental results show that long-term prediction method based on TCN has higher accuracy and less time complexity, compared with RNN (recurrent neural network), SRU (simple recurrent unit), BI-SRU (bi-directional simple recurrent unit), GRU (gated recurrent unit) and LSTM (long short-term memory). The prediction accuracy can reach up to 91.91%. The time costs of training model and prediction are reduced by an average of 64.92% and 7.24%, respectively.

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

Water ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1031
Author(s):  
Jianlong Xu ◽  
Kun Wang ◽  
Che Lin ◽  
Lianghong Xiao ◽  
Xingshan Huang ◽  
...  
Keyword(s):  
Water Quality ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Quality Data ◽  
Enterprise Management ◽  
Feature Interaction ◽  
Quality Prediction ◽  
Water Quality Data ◽  
Water Quality Prediction

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.

scholarly journals Water Quality Prediction in the Luan River Based on 1-DRCNN and BiGRU Hybrid Neural Network Model

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1273
Author(s):  
Jianzhuo Yan ◽  
Jiaxue Liu ◽  
Yongchuan Yu ◽  
Hongxia Xu
Keyword(s):  
Water Quality ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Quality Data ◽  
Prediction Algorithm ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Quality Prediction ◽  
Water Quality Data ◽  
Water Quality Prediction

The current global water environment has been seriously damaged. The prediction of water quality parameters can provide effective reference materials for future water conditions and water quality improvement. In order to further improve the accuracy of water quality prediction and the stability and generalization ability of the model, we propose a new comprehensive deep learning water quality prediction algorithm. Firstly, the water quality data are cleaned and pretreated by isolation forest, the Lagrange interpolation method, sliding window average, and principal component analysis (PCA). Then, one-dimensional residual convolutional neural networks (1-DRCNN) and bi-directional gated recurrent units (BiGRU) are used to extract the potential local features among water quality parameters and integrate information before and after time series. Finally, a full connection layer is used to obtain the final prediction results of total nitrogen (TN), total phosphorus (TP), and potassium permanganate index (COD-Mn). Our prediction experiment was carried out according to the actual water quality data of Daheiting Reservoir, Luanxian Bridge, and Jianggezhuang at the three control sections of the Luan River in Tangshan City, Hebei Province, from 5 July 2018 to 26 March 2019. The minimum mean absolute percentage error (MAPE) of this method was 2.4866, and the coefficient of determination (R2) was able to reach 0.9431. The experimental results showed that the model proposed in this paper has higher prediction accuracy and generalization than the existing LSTM, GRU, and BiGRU models.

Long-term variations of water quality in a reservoir in China

2012 ◽  
Vol 65 (8) ◽  
pp. 1454-1460 ◽  
Author(s):  
Y. Y. Chen ◽  
C. Zhang ◽  
X. P. Gao ◽  
L. Y. Wang
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Temporal Trends ◽  
Oxygen Demand ◽  
Temporal Variations ◽  
Quality Parameters ◽  
Quality Data ◽  
Water Quality Data ◽  
Yuqiao Reservoir

To study the spatial and temporal trends of water quality in the Yuqiao Reservoir (Ji County, Tianjin) in China, water quality data for ten physical and chemical parameters from three monitoring stations (S1, S2 and S3) was collected from 1989 to 2007 and from an other three stations (S4, S5 and S6) during the period of 1999–2007. A one-way ANOVA was employed to evaluate the spatial variation of water quality for each station. The results showed that there were statistically significant spatial differences for most water quality parameters except temperature and dissolved oxygen in the entire reservoir, and the concentrations of most parameters were higher in the uppermost part of the reservoir. The temporal trend study was conducted using the Seasonal–Kendall's test. The results revealed improving trends of water quality from 1989 to 2007, including a reduction of total phosphorous, temperature and biochemical oxygen demand and an increase of dissolved oxygen. High N:P ratios, ranging from 52.61 to 78.75, indicated that the reservoir was a phosphorous-limited environment. This study suggests long-term spatial and temporal variations of water quality in the Yuqiao Reservoir, which could be informative for water quality managers and scientists.

scholarly journals A Water Quality Prediction Method Based on the Deep LSTM Network Considering Correlation in Smart Mariculture

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1420 ◽  
Author(s):  
Zhuhua Hu ◽  
Yiran Zhang ◽  
Yaochi Zhao ◽  
Mingshan Xie ◽  
Jiezhuo Zhong ◽  
...  
Keyword(s):  
Water Quality ◽  
Water Temperature ◽  
Prediction Accuracy ◽  
Prediction Method ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Quality Prediction ◽  
Short Term ◽  
Water Quality Prediction ◽  
Term Prediction

An accurate prediction of cage-cultured water quality is a hot topic in smart mariculture. Since the mariculturing environment is always open to its surroundings, the changes in water quality parameters are normally nonlinear, dynamic, changeable, and complex. However, traditional forecasting methods have lots of problems, such as low accuracy, poor generalization, and high time complexity. In order to solve these shortcomings, a novel water quality prediction method based on the deep LSTM (long short-term memory) learning network is proposed to predict pH and water temperature. Firstly, linear interpolation, smoothing, and moving average filtering techniques are used to repair, correct, and de-noise water quality data, respectively. Secondly, Pearson’s correlation coefficient is used to obtain the correlation priors between pH, water temperature, and other water quality parameters. Finally, a water quality prediction model based on LSTM is constructed using the preprocessed data and its correlation information. Experimental results show that, in the short-term prediction, the prediction accuracy of pH and water temperature can reach 98.56% and 98.97%, and the time cost of the predictions is 0.273 s and 0.257 s, respectively. In the long-term prediction, the prediction accuracy of pH and water temperature can reach 95.76% and 96.88%, respectively.

Assessement of Water Quality Parameters in Some Potential Pollutant Areas from Romania

2018 ◽  
Vol 69 (8) ◽  
pp. 2045-2049
Author(s):  
Catalina Gabriela Gheorghe ◽  
Andreea Bondarev ◽  
Ion Onutu
Keyword(s):  
Water Quality ◽  
Surface Water ◽  
Surface Water Quality ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Quality Data ◽  
Chemical Parameters ◽  
Water Quality Data ◽  
Pollutant Sources ◽  
Water Quality Forecasting

Monitoring of environmental factors allows the achievement of some important objectives regarding water quality, forecasting, warning and intervention. The aim of this paper is to investigate water quality parameters in some potential pollutant sources from northern, southern and east-southern areas of Romania. Surface water quality data for some selected chemical parameters were collected and analyzed at different points from March to May 2017.

scholarly journals Chemometric analysis of drinking water quality parameters of Sagar city, Madhya Pradesh, India

2020 ◽  
Vol 31 (2) ◽  
pp. 99-105
Author(s):  
Hemant Pathak
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Quality Parameters ◽  
Chemometric Analysis ◽  
Madhya Pradesh ◽  
Drinking Water Quality ◽  
Quality Data ◽  
Multivariate Linear Regression Analysis ◽  
Water Quality Data ◽  
Entire Study

AbstractThe present study uses numerous chemometric techniques to evaluate and interpret a water quality data obtained from the drinking water resources namely municipal water (supplied by Rajghat dam on Bewas River), bore well, ground water of Sagar city, a divisional headquarter of Madhya Pradesh, India. Data was collected from May 2018 to June 2019 for 10 parameters used to assess the status of the water quality. Water quality was monitored at 15 sampling stations along the entire district. The data were analyzed using chemometric analysis such as principal component analysis, correlation matrix, multivariate linear regression analysis and hierarchical cluster analysis that reduced the data dimensions for better interpretation. Results of statistical analysis expressed that slightly higher value of BOD in some areas due to sewage contamination, need of chlorination treatment required at those places. This study also presents the value of diverse statistical methods for assessment and analysis of drinking water quality data for the reason of monitoring the effectiveness of water resource management. The study indicated that the maximum quality parameters of drinking water is in permissible limits of WHO and IS: 10500 guidelines on entire study places.

scholarly journals THE CONTRIBUTION OF GIS TO DISPLAY AND ANALYZE THE WATER QUALITY DATA COLLECTED BY A WIRELESS SENSOR NETWORK: CASE OF BOUREGREG CATCHMENT, MOROCCO

2017 ◽  
Vol IV-4/W4 ◽  
pp. 331-334
Author(s):  
S. Boubakri ◽  
H. Rhinane
Keyword(s):  
Water Quality ◽  
Wireless Sensor Networks ◽  
Wireless Sensor Network ◽  
Geographic Information Systems ◽  
Real Time ◽  
Quality Parameters ◽  
Wireless Sensor ◽  
Quality Data ◽  
Catchment Scale ◽  
Water Quality Data

The monitoring of water quality is, in most cases, managed in the laboratory and not on real time bases. Besides this process being lengthy, it doesn’t provide the required specifications to describe the evolution of the quality parameters that are of interest. This study presents the integration of Geographic Information Systems (GIS) with wireless sensor networks (WSN) aiming to create a system able to detect the parameters like temperature, salinity and conductivity in a Moroccan catchment scale and transmit information to the support station. This Information is displayed and evaluated in a GIS using maps and spatial dashboard to monitor the water quality in real time.

Sign in / Sign up

Export Citation Format

Share Document