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

Water ◽  
2018 ◽  
Vol 10 (9) ◽  
pp. 1124 ◽  
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.

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

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.

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

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.

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

Water ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 585 ◽  
Author(s):  
Yi-Fan Zhang ◽  
Peter Fitch ◽  
Peter J. Thorburn
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Dissolved Oxygen ◽  
Data Driven ◽  
Quality Data ◽  
Series Data ◽  
Support Vector ◽  
Feed Forward ◽  
Sensory Data ◽  
Water Quality Variables

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.

scholarly journals Net Ecosystem Production of a River Relying on Hydrology, Hydrodynamics and Water Quality Monitoring Stations

Water ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 783
Author(s):  
Fernando Rojano ◽  
David Huber ◽  
Ifeoma Ugwuanyi ◽  
Vadesse Noundou ◽  
Andrielle Kemajou-Tchamba ◽  
...  
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Water Quality Monitoring ◽  
Specific Conductance ◽  
Net Ecosystem Production ◽  
Quality Data ◽  
Hydrologic Simulation ◽  
Water Quality Data ◽  
Lotic Ecosystems ◽  
Ecosystem Production

Flow and water quality of rivers are highly dynamic. Water quantity and quality are subjected to simultaneous physical, chemical and biological processes making it difficult to accurately assess lotic ecosystems. Our study investigated net ecosystem production (NEP) relying on high-frequency data of hydrology, hydrodynamics and water quality. The Kanawha River, West Virginia was investigated along 52.8 km to estimate NEP. Water quality data were collected along the river using three distributed multiprobe sondes that measured water temperature, dissolved oxygen, dissolved oxygen saturation, specific conductance, turbidity and ORP hourly for 71 days. Flows along the river were predicted by means of the hydrologic and hydrodynamic models in Hydrologic Simulation Program in Fortran (HSPF). It was found that urban local inflows were correlated with NEP. However, under hypoxic conditions, local inflows were correlated with specific conductance. Thus, our approach represents an effort for the systematic integration of data derived from models and field measurements with the aim of providing an improved assessment of lotic ecosystems.

scholarly journals Visualizing Water Quality Sampling-Events in Florida

2015 ◽  
Vol II-4/W2 ◽  
pp. 73-79 ◽  
Author(s):  
M. D. Bolt
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Data Visualization ◽  
Coastal Water ◽  
Environmental Quality ◽  
Additional Data ◽  
Monitoring Program ◽  
Quality Data ◽  
Water Quality Data ◽  
Environmental Narratives

Water quality sampling in Florida is acknowledged to be spatially and temporally variable. The rotational monitoring program that was created to capture data within the state’s thousands of miles of coastline and streams, and millions of acres of lakes, reservoirs, and ponds may be partly responsible for inducing the variability as an artifact. Florida’s new dissolved-oxygen-standard methodology will require more data to calculate a percent saturation. This additional data requirement’s impact can be seen when the new methodology is applied retrospectively to the historical collection. To understand how, where, and when the methodological change could alter the environmental quality narrative of state waters requires addressing induced bias from prior sampling events and behaviors. Here stream and coastal water quality data is explored through several modalities to maximize understanding and communication of the spatiotemporal relationships. Previous methodology and expected-retrospective calculations outside the regulatory framework are found to be significantly different, but dependent on the spatiotemporal perspective. Data visualization is leveraged to demonstrate these differences, their potential impacts on environmental narratives, and to direct further review and analysis.

Hydrology and Water Quality Survey Near the Gezhouba Dam in the Winter

2013 ◽  
Vol 726-731 ◽  
pp. 3256-3261
Author(s):  
Jia Fei Zhou ◽  
Cong Feng Wang ◽  
De Fu Liu ◽  
Jing Wen Xiang ◽  
Ping Zhao ◽  
...  
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Water Temperature ◽  
Flow Velocity ◽  
Water Column ◽  
Quality Data ◽  
Chinese Sturgeon ◽  
Water Quality Data ◽  
Gezhouba Dam ◽  
Survival Condition

Filed hydrology and water quality data were collected near the Gezhouba Dam early December of 2012 to analyze the response of Chinese Sturgeon survival condition to water temperature, dissolved oxygen (DO), pH, transparency (SD) and bottom flow-velocity. The results showed that water temperature lag is unconspicuous. The water temperature of Gezhouba Dam Sanjiang (GDS) was lower than that of Gezhouba Dam River (GDR), and it hindered propagation of sturgeon eggs. DO decreased fast in the vertical water column of GDS, pH ranged from 7.5 to 7.71. The hydrology and water quality were suitable for the life condition of sturgeon eggs and fry, except index of bottom flow-velocity.

scholarly journals Fish Rescue during Streamflow Intermittency May Not Be Effective for Conservation of Rio Grande Silvery Minnow

Water ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3371
Author(s):  
Thomas P. Archdeacon ◽  
Tracy A. Diver ◽  
Justin K. Reale
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Fish Assemblages ◽  
Sublethal Effects ◽  
Rio Grande ◽  
Quality Data ◽  
Water Quality Data ◽  
Low Dissolved Oxygen ◽  
Rio Grande Silvery Minnow ◽  
Oxygen Concentrations

Streamflow intermittency can reshape fish assemblages and present challenges to recovery of imperiled species. During streamflow intermittency, fish can be subjected to a variety of stressors, including exposure to crowding, high water temperatures, and low dissolved oxygen, resulting in sublethal effects or mortality. Rescue of fishes is often used as a conservation tool to mitigate the negative impacts of streamflow intermittency. The effectiveness of such actions is rarely evaluated. Here, we use multi-year water quality data collected from isolated pools during rescue of Rio Grande silvery minnow Hybognathus amarus, an endangered minnow. We examined seasonal and diel water quality patterns to determine if fishes are exposed to sublethal and critical water temperatures or dissolved oxygen concentrations during streamflow intermittency. Further, we determined survival of rescued Rio Grande silvery minnow for 3–5 weeks post-rescue. We found that isolated pool temperatures were much warmer (>40 °C in some pools) compared to upstream perennial flows, and had larger diel fluctuations, >10 °C compared to ~5 °C, and many pools had critically low dissolved oxygen concentrations. Survival of fish rescued from isolated pools during warmer months was <10%. Reactive conservation actions such as fish rescue are often costly, and in the case of Rio Grande silvery minnow, likely ineffective. Effective conservation of fishes threatened by streamflow intermittency should focus on restoring natural flow regimes that restore the natural processes under which fishes evolved.

Forecasting Model Based on SAGA and LS-SVM for the Water Quality of Poyang Lake

2011 ◽  
Vol 347-353 ◽  
pp. 781-785
Author(s):  
Qun Cao ◽  
Bing Xiang Liu ◽  
Xiang Chen
Keyword(s):  
Water Quality ◽  
Poyang Lake ◽  
Quality Data ◽  
Support Vector ◽  
Forecasting Model ◽  
Model Parameters ◽  
Water Quality Data ◽  
Model Based ◽  
Simulated Annealing Genetic Algorithm

According to the nonlinearity and uncertainty of the water quality data samples, a forecasting model based on Simulated Annealing Genetic Algorithm(SAGA)and least squares support vector machines(LS-SVM) is proposed. Through adaptively optimizing the model parameters of LS-SVM by SAGA, we can apply the model to forecast water quality of Poyang Lake. The experimental results indicate that compared to the typical LS-SVM,the model is very practical and with higher precision.

scholarly journals River Dissolved Oxygen Prediction Based on Random Forest and LSTM

2021 ◽  
Vol 37 (5) ◽  
pp. 901-910
Author(s):  
Juan Huan ◽  
Bo Chen ◽  
Xian Gen Xu ◽  
Hui Li ◽  
Ming Bao Li ◽  
...  
Keyword(s):  
Water Quality ◽  
Random Forest ◽  
Quality Management ◽  
Dissolved Oxygen ◽  
Prediction Model ◽  
Water Quality Management ◽  
Quality Data ◽  
Mean Square ◽  
Water Quality Data ◽  
Better Than

HighlightsRandom Forest (RF) and LSTM were developed for river DO prediction.PH is the most important feature affecting DO prediction.The model base on RF is better than the model not on RF, and the dimensionality of the input data is reduced by RF.RF-LSTM model is outperformed SVR, RF-SVR, BP, RF-BP, LSTM, RNN models in DO prediction.Abstract. In order to improve the prediction accuracy of dissolved oxygen in rivers, a dissolved oxygen prediction model based on Random Forest (RF) and Long Short Term Memory networks (LSTM) is proposed. First, the Random Forest performs feature selection, which reduces the input dimension of the data and eliminates the influence of irrelevant variables on the prediction of dissolved oxygen. Then build the LSTM river dissolved oxygen prediction model to fit the relationship between water quality data and dissolved oxygen, and finally use real water quality data in the river for verification. The experimental results show that the mean square error (MSE), absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and coefficient of determination (R2) of the RF-LSTM model are 0.658, 0.528, 13.502, 0.811, 0.744, respectively, which are better than other models. The RF-LSTM model has good predictive performance and can provide a reference for river water quality management. Keywords: Dissolved oxygen prediction, LSTM, Random forest, Time series, Water quality management.

Sign in / Sign up

Export Citation Format

Share Document