Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River

Antanasijević, Davor; Pocajt, Viktor; Perić-Grujić, Aleksandra A.; Ristić, Mirjana

doi:10.1007/s00521-019-04079-y

Cited by 27 publications

(20 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar improvement was achieved for the SVR applied to estimate biochemical oxygen demand in Karun River, Western Iran. Antanasijević et al [68] presented a combination of Ward neural networks and a local similarity index for predicting DO in the Danube River. They noted the better performance of the proposed model compared to the multi-site DO evaluative approaches presented in the literature.…”

Section: Similar Workmentioning

confidence: 99%

Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks

2021

View full text Add to dashboard Cite

Predicting the level of dissolved oxygen (DO) is an important issue ensuring the sustainability of the inhabitants of a river. A prediction model can predict the DO level using a historical dataset with regard to water temperature, pH, and specific conductance for a given river. The model can be built using sophisticated computational procedures such as multi-layer perceptron-based artificial neural networks. Different types of networks can be constructed for this purpose. In this study, the authors constructed three networks, namely, multi-verse optimizer (MVO), black hole algorithm (BHA), and shuffled complex evolution (SCE). The networks were trained using the datasets collected from the Klamath River Station, Oregon, USA, for the period 2015–2018. We found that the trained networks could predict the DO level of 2019. We also found that both BHA- and SCE-based networks could predict the level of DO using a relatively simple configuration compared to that of MVO. From the viewpoints of absolute errors and Pearson’s correlation coefficient, MVO- and SCE-based networks performed better than BHA-based networks. In synopsis, the authors recommend MVO- and MLP-based artificial neural networks for predicting the DO level of a river.

show abstract

Section: Similar Workmentioning

confidence: 99%

Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks

2021

View full text Add to dashboard Cite

show abstract

“…A similar improvement was achieved for the SVR applied to estimate biochemical oxygen demand in Karun River, Western Iran. Antanasijević, et al [133] presented a combination of Ward neural networks and local similarity index for predicting the DO in the Danube River. They stated the better performance of the proposed model compared to multisite DO evaluative approaches presented in the literature.…”

Section: Introductionmentioning

confidence: 99%

Hybridizing Neural Network with Multi-Verse, Black Hole, and Shuffled Complex Evolution Optimizer Algorithms Predicting the Dissolved Oxygen

Moayedi¹,

Mosavi²

2021

Preprint

View full text Add to dashboard Cite

The great importance of estimating dissolved oxygen (DO) dictates utilizing proper evaluative models. In this work, a multi-layer perceptron (MLP) network is trained by three capable metaheuristic algorithms, namely multi-verse optimizer (MVO), black hole algorithm (BHA), and shuffled complex evolution (SCE) for predicting the DO using the data of the Klamath River Station, Oregon, US. The records (DO, water temperature, pH, and specific conductance) belonging to the water years 2015 - 2018 (USGS) are used for pattern analysis. The results of this process showed that all three hybrid models could properly infer the DO behavior. However, the BHA and SCE accomplished this task by simpler configurations. Next, the generalization ability of the developed patterns is tested using the data of the 2019 water year. Referring to the calculated mean absolute errors of 1.0161, 1.1997, and 1.0122, as well as Pearson correlation coefficients of 0.8741, 0.8453, and 0.8775, the MLPs trained by the MVO and SCE perform better than the BHA. Therefore, these two hybrids (i.e., the MLP-MVO and MLP-SCE) can be satisfactorily used for future applications.

show abstract

“…A simple rule of thumb maybe fulfills the purpose, that is random numbers must lie in the boundary between -2/I to 2/I, where I are inputs provided to the artificial neural network in any given node [12]. Many of the recent water quality studies are done by implying Artificial Neural Networks such as [13], [14], [15], [16] , [17] , [18] , [19] ,[20] , [21], [22] etc. In this study the Physico Chemical Water Quality of Manora Channel is assessed by the assessment of water quality parameter Ammonia.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Implementations on the coastal water quality of Manora channel for the years 1996 to 2014.

Ghayas

Siddiquie

Safdar

et al. 2020

International Journal of Circuits, Systems and Signal Processing

View full text Add to dashboard Cite

Neural Networks is an Important Part of Computational Intelligence, Systems Theory and Signal Processing and finds numerous important applications in Science and Engineering. Sea water quality contaminates due to the severe untreated domestic, sewage and industrial pollutants. Presence of ammonia in seawater causes the deterioration of coastal water in terms of diminution of oxygen levels which suffocates the marine lives, fishes and mangroves. Industrial, sewage and domestic effluents carried by Lyari River contaminate the Manora channel, Karachi. The aim of study is to make the clear and transparent step-wise use of Artificial Neural Networks for the data driven water quality parameters models of Manora channel (Lyari river outfall zone N 24-51-26, E 66-58-01), Karachi (Pakistan) as well as to compare the pollutant contaminant ratio with the national environmental quality standard limits and other sampling sites of Manora channel and southern east Karachi coast. In this study, Manora channel Physico-chemical water quality parameters are assessed by using Artificial Neural Network taking Biochemical Oxygen Demand (BOD), chemical oxygen Demand (COD), Bicarbonates, potential Hydrogen(pH) , Chloride(Cl) as input and Ammonia(NH3)as output. Mean Square Error and R square are used for the model assessments statistical metrics. The computational work has been done by using R-studio. This is also found that Manora channel has the contaminated level of ammonia along the other sampling stations of both southern Karachi coast (N 24-47-03 E 67-08-39) as well as the other sampling site of Manora channel Karachi coast (N 24-50-15, E 66-58-01). In spite of all contamination Ammonia is found to be within National Environmental Quality Standards limits of Pakistan.

show abstract

Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River

Cited by 27 publications

References 43 publications

Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks

Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks

Hybridizing Neural Network with Multi-Verse, Black Hole, and Shuffled Complex Evolution Optimizer Algorithms Predicting the Dissolved Oxygen

Neural Network Implementations on the coastal water quality of Manora channel for the years 1996 to 2014.

Contact Info

Product

Resources

About