Predicting the Trend of Dissolved Oxygen Based on the kPCA-RNN Model

Water quality forecasting is increasingly significant for agricultural management and environmental protection. Enormous amounts of water quality data are collected by advanced sensors, which leads to an interest in using data-driven models for predicting trends in water quality. However, the unpredictable background noises introduced during water quality monitoring seriously degrade the performance of those models. Meanwhile, artificial neural networks (ANN) with feed-forward architecture lack the capability of maintaining and utilizing the accumulated temporal information, which leads to biased predictions in processing time series data. Hence, we propose a water quality predictive model based on a combination of Kernal Principal Component Analysis (kPCA) and Recurrent Neural Network (RNN) to forecast the trend of dissolved oxygen. Water quality variables are reconstructed based on the kPCA method, which aims to reduce the noise from the raw sensory data and preserve actionable information. With the RNN’s recurrent connections, our model can make use of the previous information in predicting the trend in the future. Data collected from Burnett River, Australia was applied to evaluate our kPCA-RNN model. The kPCA-RNN model achieved R 2 scores up to 0.908, 0.823, and 0.671 for predicting the concentration of dissolved oxygen in the upcoming 1, 2 and 3 hours, respectively. Compared to current data-driven methods like Feed-forward neural network (FFNN), support vector regression (SVR) and general regression neural network (GRNN), the predictive accuracy of the kPCA-RNN model was at least 8%, 17% and 12% better than the comparative models in these three cases. The study demonstrates the effectiveness of the kPAC-RNN modeling technique in predicting water quality variables with noisy sensory data.

Download Full-text

Predicting the Trend of Dissolved Oxygen based on kPCA-RNN Model

10.20944/preprints201912.0346.v1 ◽

2019 ◽

Author(s):

Yi-Fan Zhang ◽

Peter Fitch ◽

Peter J. Thorburn

Keyword(s):

Water Quality ◽

Dissolved Oxygen ◽

Time Series Data ◽

Predictive Accuracy ◽

Data Driven ◽

Quality Data ◽

Series Data ◽

Water Quality Data ◽

Sensory Data ◽

Water Quality Variables

Water quality forecasting is increasingly significant for agricultural management and environmental protection. Enormous amounts of water quality data are increasingly being collected by advanced sensors, which leads to an interest in using data-driven models for predicting trends in water quality. However, the unpredictable background noises introduced during water quality monitoring seriously degrade the performance of those models. Meanwhile, artificial neural networks (ANN) with feed-forward architecture lack the capability of maintaining and utilizing the accumulated temporal information, which leads to biased predictions in processing time series data. Hence, we propose a water quality predictive model based on a combination of Kernal Principal Component Analysis (kPCA) and Recurrent Neural Network (RNN) to forecast the trend of dissolved oxygen. Water quality variables are reconstructed based on kPCA method, which aims to reduce the noise from the raw sensory data and preserve actionable information. With the RNN's recurrent connections, our model can make use of the previous information in predicting the trend in the future. Data collected from Burnett River, Australia was applied to evaluate our kPCA-RNN model. The kPCA-RNN model achieved R2 scores up to 0.908, 0.823 and 0.671 for predicting the concentration of dissolved oxygen in the upcoming 1, 2 and 3 hours, respectively. Compared to current data-driven methods like ANN and SVR, the predictive accuracy of the kPCA-RNN model was at least 8 %, 17 % and 21 % better than the comparative models in these 3 cases. The study demonstrates the effectiveness of the kPAC-RNN modeling technique in predicting water quality variables with noisy sensory data.

Download Full-text

The Integration of Nature-Inspired Algorithms with Least Square Support Vector Regression Models: Application to Modeling River Dissolved Oxygen Concentration

Water ◽

10.3390/w10091124 ◽

2018 ◽

Vol 10 (9) ◽

pp. 1124 ◽

Cited By ~ 20

Author(s):

Zaher Yaseen ◽

Mohammad Ehteram ◽

Ahmad Sharafati ◽

Shamsuddin Shahid ◽

Nadhir Al-Ansari ◽

...

Keyword(s):

Water Quality ◽

Dissolved Oxygen ◽

Bat Algorithm ◽

Specific Conductance ◽

Least Square ◽

Quality Data ◽

Support Vector ◽

Water Quality Data ◽

Water Quality Variables ◽

Do Concentration

The current study investigates an improved version of Least Square Support Vector Machines integrated with a Bat Algorithm (LSSVM-BA) for modeling the dissolved oxygen (DO) concentration in rivers. The LSSVM-BA model results are compared with those obtained using M5 Tree and Multivariate Adaptive Regression Spline (MARS) models to show the efficacy of this novel integrated model. The river water quality data at three monitoring stations located in the USA are considered for the simulation of DO concentration. Eight input combinations of four water quality parameters, namely, water temperature, discharge, pH, and specific conductance, are used to simulate the DO concentration. The results revealed the superiority of the LSSVM-BA model over the M5 Tree and MARS models in the prediction of river DO. The accuracy of the LSSVM-BA model compared with those of the M5 Tree and MARS models is found to increase by 20% and 42%, respectively, in terms of the root-mean-square error. All the predictive models are found to perform best when all the four water quality variables are used as input, which indicates that it is possible to supply more information to the predictive model by way of incorporation of all the water quality variables.

Download Full-text

Prediction of dissolved oxygen in urban rivers at the Three Gorges Reservoir, China: extreme learning machines (ELM) versus artificial neural network (ANN)

Water Quality Research Journal ◽

10.2166/wqrj.2019.053 ◽

2019 ◽

Vol 55 (1) ◽

pp. 106-118 ◽

Cited By ~ 6

Author(s):

Senlin Zhu ◽

Salim Heddam

Keyword(s):

Neural Network ◽

Water Quality ◽

Dissolved Oxygen ◽

Three Gorges Reservoir ◽

Model Performance ◽

Quality Data ◽

Urban Rivers ◽

Three Gorges ◽

Water Quality Data ◽

The Three Gorges

Abstract In the present study, two non-linear mathematical modelling approaches, namely, extreme learning machine (ELM) and multilayer perceptron neural network (MLPNN) were developed to predict daily dissolved oxygen (DO) concentrations. Water quality data from four urban rivers in the backwater zone of the Three Gorges Reservoir, China were used. The water quality data selected consisted of daily observed water temperature, pH, permanganate index, ammonia nitrogen, electrical conductivity, chemical oxygen demand, total nitrogen, total phosphorus and DO. The accuracy of the ELM model was compared with the standard MLPNN using several error statistics such as root mean squared error, mean absolute error, the coefficient of correlation and the Willmott index of agreement. Results showed that the ELM and MLPNN models perform well for the Wubu River, acceptably for the Yipin River and moderately for the Huaxi River, while poor model performance was obtained at the Tributary of Huaxi River. Model performance is negatively correlated with pollution level in each river. The MLPNN model slightly outperforms the ELM model in DO prediction. Overall, it can be concluded that MLPNN and ELM models can be applied for DO prediction in low-impacted rivers, while they may not be appropriate for DO modelling for highly polluted rivers. This article has been made Open Access thanks to the kind support of CAWQ/ACQE (https://www.cawq.ca).

Download Full-text

Water-Quality Data Imputation With High Percentage of Missing Values: A Machine Learning Approach

10.20944/preprints202105.0105.v1 ◽

2021 ◽

Author(s):

Rafael Rodriguez ◽

Marcos Pastorini ◽

Lorena Etcheverry ◽

Christian Chreties ◽

Mónica Fossati ◽

...

Keyword(s):

Machine Learning ◽

Water Quality ◽

Surface Water ◽

Surface Water Quality ◽

Quality Data ◽

Support Vector ◽

Data Imputation ◽

Water Quality Data ◽

Water Quality Variables ◽

Monitoring Stations

The monitoring of surface-water quality followed by water-quality modeling and analysis is essential for generating effective strategies in water-resource management. However, worldwide, particularly in developing countries, water-quality studies are limited due to the lack of a complete and reliable dataset of surface-water-quality variables. In this context, several statistical and machine-learning models were assessed for imputing water-quality data at six monitoring stations located in the Santa Lucía Chico river (Uruguay), a mixed lotic and lentic river system. The challenge of this study is represented by the high percentage of missing data (between 50% and 70%) and the high temporal and spatial variability that characterizes the water-quality variables. The competing algorithms implemented belonged to both univariate and multivariate imputation methods (inverse distance weighting (IDW), Random Forest Regressor (RFR), Ridge (R), Bayesian Ridge (BR), AdaBoost (AB), Hubber Regressor (HR), Support Vector Regressor (SVR), and K-nearest neighbors Regressor (KNNR)). According to the results, more than 76% of the imputation outcomes are considered satisfactory (NSE > 0.45). The imputation performance shows better results at the monitoring stations located inside the reservoir than the ones positioned along the mainstream. IDW was the most chosen model for data imputation.

Download Full-text

MODELING DISSOLVED OXYGEN (DO) CONCENTRATION AT KAINJI HYDROPOWER RESERVOIR USING ARTIFICIAL NEURAL NETWORK

Malaysian Journal of Civil Engineering ◽

10.11113/mjce.v30n3.521 ◽

2018 ◽

Vol 30 (3) ◽

Author(s):

Abdulrasaq Apalando Mohammed ◽

Bolaji Fatai Sule ◽

Adebayo Wahab Salami ◽

Adeniyi Ganiyu Adeogun

Keyword(s):

Neural Network ◽

Water Quality ◽

Regression Analysis ◽

Dissolved Oxygen ◽

Multiple Regression Analysis ◽

Multiple Regression ◽

Quality Data ◽

Modeling Tools ◽

Do Concentration ◽

Hydropower Reservoir

The objective of this study was to develop a multilayer perceptron neural network (MLPNN) and radial basic function neural network (RBFNN) model to predict the dissolved oxygen (DO) at some selected locations at the Kainji hydropower reservoir, Nigeria. The neural networks (NN) model was developed using water quality data collected over a six-year period (2010 to 2015). The NN structure was designed and trained using the SPSS neural network toolbox. The input variables to the NN were: pH, temperature, chloride (Cl-), PO43-, NO3-, Fe2+, and electrical conductivity (EC), while the output was the DO. The performance evaluation of the model was carried out using the coefficient of correlation (r), mean square error (MSE) and mean relative error (MRE). A positive correlation was observed between the actual and simulated DO at the four locations. The results of the simulation showed that the application of the NN and multiple regression analysis to predict DO concentration in water gave satisfactory results for all the selected locations using the two NN modeling approaches. Thus it has been demonstrated that NN modeling tools and multiple regression analysis are very efficient and useful for the computation of water quality parameters.

Download Full-text

The Dissolved Oxygen Prediction Method Based on Neural Network

Complexity ◽

10.1155/2017/4967870 ◽

2017 ◽

Vol 2017 ◽

pp. 1-6 ◽

Cited By ~ 8

Author(s):

Zhong Xiao ◽

Lingxi Peng ◽

Yi Chen ◽

Haohuai Liu ◽

Jiaqing Wang ◽

...

Keyword(s):

Neural Network ◽

Water Quality ◽

Dissolved Oxygen ◽

Prediction Models ◽

Southern China ◽

Prediction Method ◽

Water Quality Monitoring ◽

Support Vector ◽

Adjustment Process ◽

Practical Applications

The dissolved oxygen (DO) is oxygen dissolved in water, which is an important factor for the aquaculture. Using BP neural network method with the combination of purelin, logsig, and tansig activation functions is proposed for the prediction of aquaculture’s dissolved oxygen. The input layer, hidden layer, and output layer are introduced in detail including the weight adjustment process. The breeding data of three ponds in actual 10 consecutive days were used for experiments; these ponds were located in Beihai, Guangxi, a traditional aquaculture base in southern China. The data of the first 7 days are used for training, and the data of the latter 3 days are used for the test. Compared with the common prediction models, curve fitting (CF), autoregression (AR), grey model (GM), and support vector machines (SVM), the experimental results show that the prediction accuracy of the neural network is the highest, and all the predicted values are less than 5% of the error limit, which can meet the needs of practical applications, followed by AR, GM, SVM, and CF. The prediction model can help to improve the water quality monitoring level of aquaculture which will prevent the deterioration of water quality and the outbreak of disease.

Download Full-text

Pattern matching and associative artificial neural networks for water distribution system time series data analysis

Journal of Hydroinformatics ◽

10.2166/hydro.2013.057 ◽

2013 ◽

Vol 16 (3) ◽

pp. 617-632 ◽

Cited By ~ 18

Author(s):

S. R. Mounce ◽

R. B. Mounce ◽

T. Jackson ◽

J. Austin ◽

J. B. Boxall

Keyword(s):

Neural Network ◽

Neural Networks ◽

Water Quality ◽

Time Series ◽

Pattern Matching ◽

Distribution Systems ◽

Water Distribution ◽

Quality Data ◽

Series Data ◽

Artificial Neural

Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.

Download Full-text

A modeling approach to simulate impact of climate change in lake water quality: phytoplankton growth rate assessment

Water Science & Technology ◽

10.2166/wst.1998.0133 ◽

1998 ◽

Vol 37 (2) ◽

pp. 177-185 ◽

Cited By ~ 7

Author(s):

Hany Hassan ◽

Keisuke Hanaki ◽

Tomonori Matsuo

Keyword(s):

Climate Change ◽

Water Quality ◽

Growth Rate ◽

Dissolved Oxygen ◽

Lake Water ◽

Phytoplankton Growth ◽

Quality Data ◽

Model Parameters ◽

Lake Water Quality ◽

Phytoplankton Growth Rate

Global climate change induced by increased concentrations of greenhouse gases (especially CO2) is expected to include changes in precipitation, wind speed, incoming solar radiation, and air temperature. These major climate variables directly influence water quality in lakes by altering changes in flow and water temperature balance. High concentration of nutrient enrichment and expected variability of climate can lead to periodic phytoplankton blooms and an alteration of the neutral trophic balance. As a result, dissolved oxygen levels, with low concentrations, can fluctuate widely and algal productivity may reach critical levels. In this work, we will present: 1) recent results of GCMs climate scenarios downscaling project that was held at the University of Derby, UK.; 2) current/future comparative results of a new mathematical lake eutrophication model (LEM) in which output of phytoplankton growth rate and dissolved oxygen will be presented for Suwa lake in Japan as a case study. The model parameters were calibrated for the period of 1973–1983 and validated for the period of 1983–1993. Meterologic, hydrologic, and lake water quality data of 1990 were selected for the assessment analysis. Statistical relationships between seven daily meteorological time series and three airflow indices were used as a means for downscaling daily outputs of Hadley Centre Climate Model (HadCM2SUL) to the station sub-grid scale.

Download Full-text

Citizen Science Tools Reveal Changes in Estuarine Water Quality Following Demolition of Buildings

Remote Sensing ◽

10.3390/rs13091683 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1683

Author(s):

Nandini Menon ◽

Grinson George ◽

Rajamohananpillai Ranith ◽

Velakandy Sajin ◽

Shreya Murali ◽

...

Keyword(s):

Water Quality ◽

Dissolved Oxygen ◽

Citizen Science ◽

Secchi Depth ◽

Lake Water Quality ◽

Demolition Waste ◽

Water Colour ◽

Water Quality Variables ◽

The Impact

Turbidity and water colour are two easily measurable properties used to monitor pollution. Here, we highlight the utility of a low-cost device—3D printed, hand-held Mini Secchi disk (3DMSD) with Forel-Ule (FU) colour scale sticker on its outer casing—in combination with a mobile phone application (‘TurbAqua’) that was provided to laymen for assessing the water quality of a shallow lake region after demolition of four high-rise buildings on the shores of the lake. The demolition of the buildings in January 2020 on the banks of a tropical estuary—Vembanad Lake (a Ramsar site) in southern India—for violation of Indian Coastal Regulation Zone norms created public uproar, owing to the consequences of subsequent air and water pollution. Measurements of Secchi depth and water colour using the 3DMSD along with measurements of other important water quality variables such as temperature, salinity, pH, and dissolved oxygen (DO) using portable instruments were taken for a duration of five weeks after the demolition to assess the changes in water quality. Paired t-test analyses of variations in water quality variables between the second week of demolition and consecutive weeks up to the fifth week showed that there were significant increases in pH, dissolved oxygen, and Secchi depth over time, i.e., the impact of demolition waste on the Vembanad Lake water quality was found to be relatively short-lived, with water clarity, colour, and DO returning to levels typical of that period of year within 4–5 weeks. With increasing duration after demolition, there was a general decrease in the FU colour index to 17 at most stations, but it did not drop to 15 or below, i.e., towards green or blue colour indicating clearer waters, during the sampling period. There was no significant change in salinity from the second week to the fifth week after demolition, suggesting little influence of other factors (e.g., precipitation or changes in tidal currents) on the inferred impact of demolition waste. Comparison with pre-demolition conditions in the previous year (2019) showed that the relative changes in DO, Secchi depth, and pH were very high in 2020, clearly depicting the impact of demolition waste on the water quality of the lake. Match-ups of the turbidity of the water column immediately before and after the demolition using Sentinel 2 data were in good agreement with the in situ data collected. Our study highlights the power of citizen science tools in monitoring lakes and managing water resources and articulates how these activities provide support to Sustainable Development Goal (SDG) targets on Health (Goal 3), Water quality (Goal 6), and Life under the water (Goal 14).

Download Full-text