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

Water ◽  
2019 ◽  
Vol 11 (7) ◽  
pp. 1317 ◽  
Author(s):  
Jianzhuo Yan ◽  
Xinyue Chen ◽  
Yongchuan Yu ◽  
Xiaojuan Zhang
Keyword(s):  
Water Quality ◽  
Quality Indicators ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Quality Data ◽  
Short Term ◽  
Water Quality Data ◽  
Swarm Optimization ◽  
Water Quality Indicators ◽  
Long Short Term Memory

Water quality data cleaning is important for the management of water environments. A framework for water quality time series cleaning is proposed in this paper. Considering the nonlinear relationships among water quality indicators, support vector regression (SVR) is used to forecast water quality indicators when some indicators are missing or when they show abnormal values at a certain point in time. Considering the time series of water quality information, long short-term memory (LSTM) networks are used to forecast water quality indicators when all indicators are missing at a certain point in time. A parallel model based on particle swarm optimization (PSO) and LSTM is realized based on a microservices architecture to improve the efficiency of model execution and the predictive accuracy of the LSTM networks. The performance of the model is evaluated in terms of the mean absolute error (MAE) and root-mean-square error (RMSE). Inlet water quality data from a wastewater treatment plant in Gaobeidian, Beijing, China is considered as a case study to examine the effectiveness of this approach. The experimental results reveal that this model has better predictive accuracy than other data-driven models because of smaller MAE and RMSE and has an advantage in terms of time consumption compared with standalone serial algorithms.

scholarly journals Application of Rough Set Theory to Water Quality Analysis: A Case Study

Data ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. 50 ◽  
Author(s):  
Maryam Zavareh ◽  
Viviana Maggioni
Keyword(s):  
Water Quality ◽  
Quality Indicators ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Specific Conductivity ◽  
Quality Analysis ◽  
Quality Data ◽  
Water Quality Data ◽  
Water Quality Indicators

This work proposes an approach to analyze water quality data that is based on rough set theory. Six major water quality indicators (temperature, pH, dissolved oxygen, turbidity, specific conductivity, and nitrate concentration) were collected at the outlet of the watershed that contains the George Mason University campus in Fairfax, VA during three years (October 2015–December 2017). Rough set theory is applied to monthly averages of the collected data to estimate one indicator (decision attribute) based on the remainder indicators and to determine what indicators (conditional attributes) are essential (core) to predict the missing indicator. The redundant attributes are identified, the importance degree of each attribute is quantified, and the certainty and coverage of any detected rule(s) is evaluated. Possible decision making rules are also assessed and the certainty coverage factor is calculated. Results show that the core water quality indicators for the Mason watershed during the study period are turbidity and specific conductivity. Particularly, if pH is chosen as a decision attribute, the importance degree of turbidity is higher than the one of conductivity. If the decision attribute is turbidity, the only indispensable attribute is specific conductivity and if specific conductivity is the decision attribute, the indispensable attribute beside turbidity is temperature.

scholarly journals Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models

2020 ◽  
Vol 12 (6) ◽  
pp. 2570 ◽  
Author(s):  
Thanongsak Xayasouk ◽  
HwaMin Lee ◽  
Giyeol Lee
Keyword(s):  
Air Quality ◽  
Urban Areas ◽  
Short Term Memory ◽  
Batch Size ◽  
Quality Data ◽  
Short Term ◽  
Optimal Learning ◽  
Term Memory ◽  
Batch Sizes ◽  
Long Short Term Memory

Many countries worldwide have poor air quality due to the emission of particulate matter (i.e., PM10 and PM2.5), which has led to concerns about human health impacts in urban areas. In this study, we developed models to predict fine PM concentrations using long short-term memory (LSTM) and deep autoencoder (DAE) methods, and compared the model results in terms of root mean square error (RMSE). We applied the models to hourly air quality data from 25 stations in Seoul, South Korea, for the period from 1 January 2015, to 31 December 2018. Fine PM concentrations were predicted for the 10 days following this period, at an optimal learning rate of 0.01 for 100 epochs with batch sizes of 32 for LSTM model, and DAEs model performed best with batch size 64. The proposed models effectively predicted fine PM concentrations, with the LSTM model showing slightly better performance. With our forecasting model, it is possible to give reliable fine dust prediction information for the area where the user is located.

scholarly journals Implementation of Long-Short Term Memory Neural Network (LSTM) for Predicting The Water Quality Parameters in Sungai Selangor

2021 ◽  
Vol 6 (4) ◽  
pp. 40-49
Author(s):  
Nur Natasya Mohd Anuar ◽  
Nur Fatihah Fauzi ◽  
Huda Zuhrah Ab Halim ◽  
Nur Izzati Khairudin ◽  
Nurizatul Syarfinas Ahmad Bakhtiar ◽  
...  
Keyword(s):  
Water Quality ◽  
Short Term Memory ◽  
Oxygen Demand ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Short Term ◽  
Term Memory ◽  
Quality Of Water ◽  
Long Short Term Memory

Predictions of future events must be factored into decision-making. Predictions of water quality are critical to assist authorities in making operational, management, and strategic decisions to keep the quality of water supply monitored under specific criteria. Taking advantage of the good performance of long short-term memory (LSTM) deep neural networks in time-series prediction, the purpose of this paper is to develop and train a Long-Short Term Memory (LSTM) Neural Network to predict water quality parameters in the Selangor River. The primary goal of this study is to predict five (5) water quality parameters in the Selangor River, namely Biochemical Oxygen Demand (BOD), Ammonia Nitrogen (NH3-N), Chemical Oxygen Demand (COD), pH, and Dissolved Oxygen (DO), using secondary data from different monitoring stations along the river basin. The accuracy of this method was then measured using RMSE as the forecast measure. The results show that by using the Power of Hydrogen (pH), the dataset yielded the lowest RMSE value, with a minimum of 0.2106 at station 004 and a maximum of 1.2587 at station 001. The results of the study indicate that the predicted values of the model and the actual values were in good agreement and revealed the future developing trend of water quality parameters, showing the feasibility and effectiveness of using LSTM deep neural networks to predict the quality of water parameters.

scholarly journals The Fluctuation of Water Quality of Ci Lutung flow areas in Majalengka and Sumedang.

2018 ◽  
Vol 73 ◽  
pp. 04013
Author(s):  
Deddy Caesar Agusto ◽  
Eko Kusratmoko
Keyword(s):  
Water Quality ◽  
Point Source ◽  
Agricultural Land ◽  
Quality Data ◽  
Water Quality Data ◽  
Water Quality Indicators ◽  
Quality Of Water ◽  
The Moment ◽  
The Impact

The river is the main source of water in Indonesia, which at the moment, this quality tends to get worse and is no longer worth consuming for various needs. The cause of the pollution is the entry of pollutants both point source (industrial waste) and non-point source (residential and agricultural land). Rainfall can be a non-point source pollutant agent from a watershed to a water body. The impact of rainfall on increasing concentrations of pollutants is very significant, especially the high intensity rainfall that falls after the long dry season. In this study, water quality data is obtained from river outlets located in Damkamun taken every 30 minutes during the rainfall event so that fluctuation in water quality can be seen. Water quality indicators studied in this research are TDS, DHLNitrate, Phosphate and Ph. The author, in analyzing, using rainfall Himawari 8 which is obtained every 10 minutes. The result shows that rainfall is directly related to the water flow and the fluctuation of the discharge affects the water quality. From the calculations, the chemical quality of water is also influenced by the use of land in the watershed. Nitrate value increases when the occurrence of rain occurs in land use while phosphate experiences a high value during the event.

Sign in / Sign up

Export Citation Format

Share Document