Water quality prediction based on recurrent neural network and improved evidence theory: a case study of Qiantang River, China

Li, Lei; Jiang, Peng; Xu, Hao; Lin, Guang; Guo, Dong Ming; Wu, Hui

doi:10.1007/s11356-019-05116-y

Cited by 111 publications

(39 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A constructive neural network that aims to solve the problems of the determination of potential neurons which are not relevant to the output layer [49] MNNs A special feedforward network Choosing the neural network which have the maximum similarity between the inputs and centroids of the cluster Solving the problem of low prediction accuracy [30,50] RNNs The RNNs are developed with the development of deep learning Solving the problems of long-term dependence which are not captured by the feedforward network [12,31,38,51,52] LSTMs Its structure is similar to RNNs Memory cell state is added to hidden layer Addressing the well-known vanishing gradient problem of RNNs [15,26,45,53,54] TLRN Its structure is similar to MLPs It has the local recurrent connections in the hidden layer…”

Section: Mlpsmentioning

confidence: 99%

“…Liu et al [3] pointed out that if more historical data were available [15], ANN models may provide better predictions than a relatively small data set. Antanasijević et al [41] tested the performance of RNN, GRNN, and MLP in small samples prediction.…”

Section: Artificial Neural Network Models For Water Quality Predictionmentioning

confidence: 99%

“…Results indicated that this hybrid model could reduce error whether in root mean square or mean absolute error. Jin et al [152] proposed an improvement variant namely improved genetic algorithm (IGA) to avoid the situation where excellent individuals are discarded by the GA. Li et al [15] introduced evidence theory, that has good data fusion ability, since it is able to reason with uncertainty to synthesize the evidence from SRU, Gated Recurrent Unit (GRU), LSTM sources in DO, pH, TP prediction, and eventually reached a certain level of belief. The improved probability assignment function of the evidence theory, designed based on the softmax function, could solve the failure of weight allocation problems existing in the traditional probability assignment function.…”

Section: Artificial Neural Network Models For Water Quality Predictionmentioning

confidence: 99%

See 2 more Smart Citations

A Review of the Artificial Neural Network Models for Water Quality Prediction

et al. 2020

View full text Add to dashboard Cite

Water quality prediction plays an important role in environmental monitoring, ecosystem sustainability, and aquaculture. Traditional prediction methods cannot capture the nonlinear and non-stationarity of water quality well. In recent years, the rapid development of artificial neural networks (ANNs) has made them a hotspot in water quality prediction. We have conducted extensive investigation and analysis on ANN-based water quality prediction from three aspects, namely feedforward, recurrent, and hybrid architectures. Based on 151 papers published from 2008 to 2019, 23 types of water quality variables were highlighted. The variables were primarily collected by the sensor, followed by specialist experimental equipment, such as a UV-visible photometer, as there is no mature sensor for measurement at present. Five different output strategies, namely Univariate-Input-Itself-Output, Univariate-Input-Other-Output, Multivariate-Input-Other(multi), Multivariate-Input-Itself-Other-Output, and Multivariate-Input-Itself-Other (multi)-Output, are summarized. From results of the review, it can be concluded that the ANN models are capable of dealing with different modeling problems in rivers, lakes, reservoirs, wastewater treatment plants (WWTPs), groundwater, ponds, and streams. The results of many of the review articles are useful to researchers in prediction and similar fields. Several new architectures presented in the study, such as recurrent and hybrid structures, are able to improve the modeling quality of future development.

show abstract

Section: Mlpsmentioning

confidence: 99%

Section: Artificial Neural Network Models For Water Quality Predictionmentioning

confidence: 99%

Section: Artificial Neural Network Models For Water Quality Predictionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of the Artificial Neural Network Models for Water Quality Prediction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As an example, Granado et al (2019) use Bayesian networks successfully for beach litter forecasting. Various probabilistic methods are applied in marine sciences for similar (transport and fate of MPs) problems (e.g., an entropy theory is used for suspended sediment transport (Khorram and Egril 2018), ensemble model with uncertainty analysis is applied for forecasting of chlorophyll-a concentrations (Shamshirband et al 2019), recurrent neural network and improved evidence theory predicts water quality (Li et al 2019), machine learning approach is used to predict the settling velocity of non-cohesive particles (Goldstein and Coco 2014)). Such models may help in answering the most general and most practically needed questions related to the contamination of environments by MPs, considered as an ensemble of particles, with a wide range of properties permanently changing with time.…”

Section: Modelling Of Mps Transportcurrent Progress and Open Questionsmentioning

confidence: 99%

Transport of marine microplastic particles: why is it so difficult to predict?

Khatmullina

Chubarenko

2019

Anthropocene Coasts

View full text Add to dashboard Cite

Marine microplastic particles (MPs, <5 mm) exhibit wide ranges of densities, sizes, and shapes, so that the entire MPs “ensemble” at every time instant can be characterized by continuous distributions of these parameters. Accordingly, this community of particles demonstrates distributions of dynamical properties, such as sinking or rising velocity, critical shear stress, and the re-suspension threshold. Moreover, all the MPs’ properties vary significantly with the time spent in marine environment and with particular conditions experienced by the particle on its journey. A brief review of the present-day numerical efforts towards prediction of MPs transport shows the prevalence of the Lagrangian particle tracking approach, especially for floating litter. In a broader context, the present practice of MPs transport modelling follows the “selective” strategy (e.g., only a certain sub-class of MPs, or specific processes, are considered, sometimes in only one- or two-dimensional setting). The heterogeneous nature of MPs, their enormous longevity and movability in marine environment, and the wide spectrum of the involved environmental processes suggest further integration (or coupling) of different models in future, as well as application of other types of models (ensemble modeling, chaos theory approaches, machine learning, etc.) to the problems of MPs transport and fate in the marine environment.

show abstract

“…Predicting future water quality changes is a prerequisite for early water pollution control [ 3 ] and plays a crucial role in environmental monitoring, ecosystem management, and human health [ 1 ]. As a result, water quality prediction has tremendous practical significance [ 4 , 5 , 6 ] as an essential means of preventing water pollution in any catchment [ 7 ]. As influenced by natural and human-induced occurrences [ 8 ], the water quality of any catchment serves as scientific evidence for economic development, commercial planning, and water resources protection from future contamination of that catchment [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

The Use of Artificial Neural Networks to Predict the Physicochemical Characteristics of Water Quality in Three District Municipalities, Eastern Cape Province, South Africa

Setshedi

Mutingwende

Ngqwala

2021

IJERPH

View full text Add to dashboard Cite

Reliable prediction of water quality changes is a prerequisite for early water pollution control and is vital in environmental monitoring, ecosystem sustainability, and human health. This study uses Artificial Neural Network (ANN) technique to develop the best model fits to predict water quality parameters by employing multilayer perceptron (MLP) neural network and the radial basis function (RBF) neural network, using data collected from three district municipalities. Two input combination models, MLP-4-5-4 and MLP-4-9-4, were trained, verified, and tested for their predictive performance ability, and their physicochemical prediction accuracy was compared by using each model’s observed data with the predicted data. The MLP-4-5-4 model showed a better understanding of the data sets and water quality predictive ability giving an MSE of 39.06589 and a correlation coefficient (R2) of the observed and the predicted water quality of 0.989383 compared to the MLP-4-9-4 model (R2 = 0.993532, MSE = 39.03087). These results apply to natural water resources management in South Africa and similar catchment systems. The MLP-4-5-4 system can be scaled up for future water quality prediction of the Waste Water Treatment Plants (WWTPs), groundwater, and surface water while raising awareness among the public and industry on future water quality.

show abstract

Water quality prediction based on recurrent neural network and improved evidence theory: a case study of Qiantang River, China

Cited by 111 publications

References 47 publications

A Review of the Artificial Neural Network Models for Water Quality Prediction

A Review of the Artificial Neural Network Models for Water Quality Prediction

Transport of marine microplastic particles: why is it so difficult to predict?

The Use of Artificial Neural Networks to Predict the Physicochemical Characteristics of Water Quality in Three District Municipalities, Eastern Cape Province, South Africa

Contact Info

Product

Resources

About