scholarly journals Comparison of Forecasting Models for Real-Time Monitoring of Water Quality Parameters Based on Hybrid Deep Learning Neural Networks

Water ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 1547
Author(s):  
Jian Sha ◽  
Xue Li ◽  
Man Zhang ◽  
Zhong-Liang Wang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Deep Learning ◽  
Real Time ◽  
Best Management Practices ◽  
Input Data ◽  
Management Practices ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Real Time Monitoring

Accurate real-time water quality prediction is of great significance for local environmental managers to deal with upcoming events and emergencies to develop best management practices. In this study, the performances in real-time water quality forecasting based on different deep learning (DL) models with different input data pre-processing methods were compared. There were three popular DL models concerned, including the convolutional neural network (CNN), long short-term memory neural network (LSTM), and hybrid CNN–LSTM. Two types of input data were applied, including the original one-dimensional time series and the two-dimensional grey image based on the complete ensemble empirical mode decomposition algorithm with adaptive noise (CEEMDAN) decomposition. Each type of input data was used in each DL model to forecast the real-time monitoring water quality parameters of dissolved oxygen (DO) and total nitrogen (TN). The results showed that (1) the performances of CNN–LSTM were superior to the standalone model CNN and LSTM; (2) the models used CEEMDAN-based input data performed much better than the models used the original input data, while the improvements for non-periodic parameter TN were much greater than that for periodic parameter DO; and (3) the model accuracies gradually decreased with the increase of prediction steps, while the original input data decayed faster than the CEEMDAN-based input data and the non-periodic parameter TN decayed faster than the periodic parameter DO. Overall, the input data preprocessed by the CEEMDAN method could effectively improve the forecasting performances of deep learning models, and this improvement was especially significant for non-periodic parameters of TN.

Data driven methods for real time flood, drought and water quality monitoring: applications for Internet of Water

2020 ◽  
Author(s):  
Brianna Pagán ◽  
Nele Desmet ◽  
Piet Seuntjens ◽  
Erik Bollen ◽  
Bart Kuijpers
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Water Quality ◽  
Data Assimilation ◽  
Real Time ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Weather Data ◽  
Model Estimate ◽  
The University

<p>The Internet of Water (IoW) is a large-scale permanent sensor network with 2500 small, energy-efficient wireless water quality sensors spread across Flanders, Belgium. This intelligent water management system will permanently monitor water quality and quantity in real time. Such a dense network of sensors with high temporal resolution (sub-hourly) will provide unprecedented volumes of data for drought, flood and pollution management, prediction and decisions. While traditional physical hydrological models are obvious choices for utilizing such a dataset, computational costs or limitations must be considered when working in real time decision making.</p><p>In collaboration with the Flemish Institute for Technological Research (VITO) and the University of Hasselt, we present several data mining and machine learning initiatives which support the IoW. Examples include interpolating grab sample measurements to river stretches to monitor salinity intrusion. A shallow feed forward neural network is trained on historical grab samples using physical characteristics of the river stretches (i.e. soil properties, ocean connectivity). Such a system allows for salinity monitoring without complex convection-diffusion modeling, and for estimating salinity in areas with less monitoring stations. Another highlighted project is the coupling of neural network and data assimilation schemes for water quality forecasting. A long short-term memory recurrent neural network is trained on historical water quality parameters and remotely sensed spatially distributed weather data. Using forecasted weather data, a model estimate of water quality parameters are obtained from the neural network. A Newtonian nudging data assimilation scheme further corrects the forecast leveraging previous day observations, which can aid in the correction for non-point or non-weather driven pollution influences. Calculations are supported by an optimized database system developed by the University of Hasselt which further exploits data mining techniques to estimate water movement and timing through the Flanders river network system. As geospatial data increases exponentially in both temporal and spatial resolutions, scientists and water managers must consider the tradeoff between computational resources and physical model accuracy. These type of hybrid approaches allows for near real-time analysis without computational limitations and will further support research to make communities more climate resilient.</p>

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

Classification and Prediction of Goldfish Population and Water Quality Using a Potentiometric E-Tongue

2017 ◽  
Vol 60 (4) ◽  
pp. 1037-1044
Author(s):  
Zhenbo Wei ◽  
Yu Zhao ◽  
Jun Wang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Pattern Recognition ◽  
Comprehensive Evaluation ◽  
Back Propagation ◽  
Correlation Coefficients ◽  
Principal Component ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Pattern Recognition Methods

Abstract. In this study, a potentiometric E-tongue was employed for comprehensive evaluation of water quality and goldfish population with the help of pattern recognition methods. Four water quality parameters, i.e., pH and concentrations of dissolved oxygen (DO), nitrite (NO2-N), and ammonium (NH3-N), were tested by conventional analysis methods. The differences in water quality parameters between samples were revealed by two-way analysis of variance (ANOVA). The cultivation days and goldfish population were classified well by principal component analysis (PCA) and canonical discriminant analysis (CDA), and the distribution of each sample was clearer in CDA score plots than in PCA score plots. The cultivation days, goldfish population, and water parameters were predicted by a T-S fuzzy neural network (TSFNN) and back-propagation artificial neural network (BPANN). BPANN performed better than TSFNN in the prediction, and all fitting correlation coefficients were >0.90. The results indicated that the potentiometric E-tongue coupled with pattern recognition methods could be applied as a rapid method for the determination and evaluation of water quality and goldfish population. Keywords: Classify, E-tongue, Goldfish water, Prediction.

scholarly journals Research and Design of Distributed IoT Water Environment Monitoring System Based on LoRa

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Wei Chen ◽  
Xiao Hao ◽  
JianRong Lu ◽  
Kui Yan ◽  
Jin Liu ◽  
...  
Keyword(s):  
Water Quality ◽  
Water Temperature ◽  
Real Time ◽  
Monitoring System ◽  
Water Environment ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Environment Monitoring ◽  
Long Distance ◽  
Internet Of Things Technology

In order to solve the problems of high labor cost, long detection period, and low degree of information in current water environment monitoring, this paper proposes a lake water environment monitoring system based on LoRa and Internet of Things technology. The system realizes remote collection, data storage, dynamic monitoring, and pollution alarm for the distributed deployment of multisensor node information (water temperature, pH, turbidity, conductivity, and other water quality parameters). Moreover, the system uses STM32L151C8T6 microprocessor and multiple types of water quality sensors to collect water quality parameters in real time, and the data is packaged and sent to the LoRa gateway remotely by LoRa technology. Then, the gateway completes the bridging of LoRa link to IP link and forwards the water quality information to the Alibaba Cloud server. Finally, end users can realize the water quality control of monitored water area by monitoring management platform. The experimental results show that the system has a good performance in terms of real-time data acquisition accuracy, data transmission reliability, and pollution alarm success rate. The average relative errors of water temperature, pH, turbidity, and conductivity are 0.31%, 0.28%, 3.96%, and 0.71%, respectively. In addition, the signal reception strength of the system within 2 km is better than -81 dBm, and the average packet loss rate is only 94%. In short, the system’s high accuracy, high reliability, and long distance characteristics meet the needs of large area water quality monitoring.

scholarly journals A Prediction Model Based on Deep Belief Network and Least Squares SVR Applied to Cross-Section Water Quality

Water ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1929
Author(s):  
Jianzhuo Yan ◽  
Ya Gao ◽  
Yongchuan Yu ◽  
Hongxia Xu ◽  
Zongbao Xu
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Prediction Model ◽  
Least Squares ◽  
Quality Parameters ◽  
Deep Belief Network ◽  
Water Quality Parameters ◽  
Series Data ◽  
Belief Network ◽  
The Mean

Recently, the quality of fresh water resources is threatened by numerous pollutants. Prediction of water quality is an important tool for controlling and reducing water pollution. By employing superior big data processing ability of deep learning it is possible to improve the accuracy of prediction. This paper proposes a method for predicting water quality based on the deep belief network (DBN) model. First, the particle swarm optimization (PSO) algorithm is used to optimize the network parameters of the deep belief network, which is to extract feature vectors of water quality time series data at multiple scales. Then, combined with the least squares support vector regression (LSSVR) machine which is taken as the top prediction layer of the model, a new water quality prediction model referred to as PSO-DBN-LSSVR is put forward. The developed model is valued in terms of the mean absolute error (MAE), the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the coefficient of determination ( R 2 ). Results illustrate that the model proposed in this paper can accurately predict water quality parameters and better robustness of water quality parameters compared with the traditional back propagation (BP) neural network, LSSVR, the DBN neural network, and the DBN-LSSVR combined model.

scholarly journals Operational Forest Stream Crossings Effects on Water Quality in the Virginia Piedmont

2011 ◽  
Vol 35 (3) ◽  
pp. 123-130 ◽  
Author(s):  
Wallace M. Aust ◽  
Mathew B. Carroll ◽  
M. Chad Bolding ◽  
C. Andrew Dolloff
Keyword(s):  
Water Quality ◽  
Best Management Practices ◽  
Management Practices ◽  
Quality Parameters ◽  
Site Factors ◽  
Concentration Data ◽  
Individual Site ◽  
Forest Stream ◽  
Randomized Design ◽  
Portable Bridges

Abstract Water quality indices were examined for paired upstream and downstream samples for 23 operational stream crossings and approaches during four periods. Stream crossings were (1) portable bridges (BRIDGE), (2) culverts backfilled with poles (POLE), (3) culverts with earth backfill (CULVERT), and (4) reinforced fords (FORD). The four operational periods were (1) prior to crossing installation (INITIAL), (2) after installation (INSTALL), (3) during harvest (HARVEST), and (4) after road closure (CLOSURE). Differences (Δ) in water samples collected above and below stream crossings were analyzed for Δtotal dissolved solids (ΔTDS), ΔpH, Δconductivity, Δtemperature, and Δsediment concentration. Data were analyzed as a completely randomized design with unequal replication (four to seven replications). Significant differences were observed (α < 0.10) among crossing types for Δtemperature, ΔTDS, ΔpH, and Δconductivity. Overall, the least disruptive crossing type for water quality was BRIDGE, but road standards and approach characteristics were also important. Modeled estimates of erosion demonstrated that CULVERT approaches had higher potential erosion than other crossings. Water quality parameters were most negatively affected during INSTALL and HARVEST and were apparently improving during CLOSURE. Permanent crossings were associated with significantly greater temperatures than temporary crossings, likely because of increased width of streamside management zone removal. Water quality effects could be minimized by installing appropriate best management practices during all harvest periods rather than waiting until CLOSURE. Findings should be used cautiously because individual site factors such as climate, site, soil, and operational variability will alter effects.

scholarly journals Can Decomposition Approaches Always Enhance Soft Computing Models? Predicting the Dissolved Oxygen Concentration in the St. Johns River, Florida

2019 ◽  
Vol 9 (12) ◽  
pp. 2534 ◽  
Author(s):  
Mohammad Zounemat-Kermani ◽  
Youngmin Seo ◽  
Sungwon Kim ◽  
Mohammad Ali Ghorbani ◽  
Saeed Samadianfard ◽  
...  
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Dissolved Oxygen ◽  
Soft Computing ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Performance Criteria ◽  
Input Combination ◽  
Do Concentration ◽  
Computing Models

This study evaluates standalone and hybrid soft computing models for predicting dissolved oxygen (DO) concentration by utilizing different water quality parameters. In the first stage, two standalone soft computing models, including multilayer perceptron (MLP) neural network and cascade correlation neural network (CCNN), were proposed for estimating the DO concentration in the St. Johns River, Florida, USA. The DO concentration and water quality parameters (e.g., chloride (Cl), nitrogen oxides (NOx), total dissolved solid (TDS), potential of hydrogen (pH), and water temperature (WT)) were used for developing the standalone models by defining six combinations of input parameters. Results were evaluated using five performance criteria metrics. Overall results revealed that the CCNN model with input combination III (CCNN-III) provided the most accurate predictions of DO concentration values (root mean square error (RMSE) = 1.261 mg/L, Nash-Sutcliffe coefficient (NSE) = 0.736, Willmott’s index of agreement (WI) = 0.919, R2 = 0.801, and mean absolute error (MAE) = 0.989 mg/L) for the standalone model category. In the second stage, two decomposition approaches, including discrete wavelet transform (DWT) and variational mode decomposition (VMD), were employed to improve the accuracy of DO concentration using the MLP and CCNN models with input combination III (e.g., DWT-MLP-III, DWT-CCNN-III, VMD-MLP-III, and VMD-CCNN-III). From the results, the DWT-MLP-III and VMD-MLP-III models provided better accuracy than the standalone models (e.g., MLP-III and CCNN-III). Comparison of the best hybrid soft computing models showed that the VMD-MLP-III model with 4 intrinsic mode functions (IMFs) and 10 quadratic penalty factor (VMD-MLP-III (K = 4 and α = 10)) model yielded slightly better performance than the DWT-MLP-III with Daubechies-6 (D6) and Symmlet-6 (S6) (DWT-MLP-III (D6 and S6)) models. Unfortunately, the DWT-CCNN-III and VMD-CCNN-III models did not improve the performance of the CCNN-III model. It was found that the CCNN-III model cannot be used to apply the hybrid soft computing modeling for prediction of the DO concentration. Graphical comparisons (e.g., Taylor diagram and violin plot) were also utilized to examine the similarity between the observed and predicted DO concentration values. The DWT-MLP-III and VMD-MLP-III models can be an alternative tool for accurate prediction of the DO concentration values.

Sign in / Sign up

Export Citation Format

Share Document