Simultaneous modelling and forecasting of hourly dissolved oxygen concentration (DO) using radial basis function neural network (RBFNN) based approach: a case study from the Klamath River, Oregon, USA

Heddam, Salim

doi:10.1007/s40808-016-0197-4

Cited by 33 publications

(12 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study results show a consistency with other studies. For example, Heddam [54] in a separate study demonstrated that water temperature and pH can predict DO levels with an enough level of confidence. The results and insight from this study can also offer practical benefits.…”

Section: Discussionmentioning

confidence: 99%

Dissolved oxygen concentration predictions for running waters with different land use land cover using a quantile regression forest machine learning technique

Ahmed

Lin

2021

Journal of Hydrology

View full text Add to dashboard Cite

Dissolved oxygen (DO) is a key indicator in the study of the ecological health of rivers. Modeling DO is a major challenge due to complex interactions among various process components of it. Considering the vital importance of it in water bodies, the accurate prediction of DO is a critical issue in ecosystem management. Given the intricacy of the current process-based water quality models, a data-driven model could be an effective alternative tool. In this study, a random forest machine learning technique is employed to predict the DO level by identifying its major drivers. Time-series of half-hourly water quality data, spanning from 2007 to 2019, for the South Branch Potomac River near Springfield, WV, are obtained from the United States Geological Survey database. Key drivers are identified, and models are formulated for different scenarios of input variables. The model is calibrated for each input scenario using 80% of the data. Water temperature and pH are found to be the most influential predictors of DO. However, satisfactory model performance is achieved by considering water temperature, pH, and specific conductance as input variables. The model validation is made by predicting DO concentrations for the remaining 20% of the data. The comparison with the traditional multiple linear regression method shows that the random forest model performs significantly better. The study insights are, therefore, expected to be useful to estimate stream/river DO levels at various sites with a minimum number of predictors and help build a sturdy framework for ecosystem health management across an environmental gradient.

show abstract

Section: Discussionmentioning

confidence: 99%

Dissolved oxygen concentration predictions for running waters with different land use land cover using a quantile regression forest machine learning technique

Ahmed

Lin

2021

Journal of Hydrology

View full text Add to dashboard Cite

show abstract

“…The neurons are organized in layers and interconnected with weighted connections corresponding to human brain synapses. Multilayer perceptron neural network (MLPNN) is the most common type of ANN, and it has been applied for many applications include river flow forecasting, pigment concentration in a river, and water quality prediction [26]- [28]. Its architecture can be described, as shown in Fig.…”

Section: Basics Of Artificial Neural Networkmentioning

confidence: 99%

“…Assuming the number of input parameters is denoted by k, and the number of neurons in the hidden layer is given as m. Mathematically, the input to the output structure of the MLPNN can be formulated as follows [26]:…”

Section: Basics Of Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Intelligence in Fish Feeding System for Dispensing Feed Based on Fish Feeding Intensity

et al. 2020

View full text Add to dashboard Cite

The amount of feed dispense to match fish appetite plays a significant role in increasing fish cultivation. However, measuring the quantity of fish feed intake remains a critical challenge. To addressed this problem, this paper proposed an intelligent fish feeding regime system using fish behavioral vibration analysis and artificial neural networks. The model was developed using acceleration and angular velocity data obtained through a data logger that incorporated a triaxial accelerometer, magnetometer, and gyroscope for predicting fish behavioral activities. To improve the system accuracy, we developed a novel 8-directional Chain Code generator algorithm that extracts the vectors representing escape, swimming, and feeding activities. The set of sequence vectors extracted was further processed using Discrete Fourier Transform, and then the Fourier Descriptors of the individual activity representations were computed. These Fourier Descriptors are fed into an artificial neural network, the results of which are evaluated and compared with the Fourier Descriptors obtained directly from the acceleration and angular velocity data. The results show that the developed model using Fourier Descriptors obtained from Chain Code has an accuracy of 100%. In comparison, the developed classifier using Fourier Descriptors obtained directly from the fish movements acceleration, and angular velocity has an accuracy of 35.60%. These results showed that the proposed system could be used in dispensing feeds successfully without human intervention based on the fish requirements. INDEX TERMS Accelerometer, artificial neural network, aquaculture, chain code, fish, fish activities, fish feeding system, Fourier descriptor, IoT devices.

show abstract

“…Para comparar os resultados do modelo desenvolvido foram utilizados os modelos de regressão linear e perceptron multi-camada e concluiu que o modelo proposto apresenta melhor resultado de previsão quando o parâmetro apresenta alta variabilidade no conjunto de dados. [Heddam 2016] comparou a capacidade dos modelos Radial Basis Function Neural Network (RBFNN) e Multilayer Rede Neural Perceptron (MLPNN) para modelagem simultânea e previsão de concentração de OD, utilizando variáveis (pH, TE, SC e SD) da qualidade daágua e valores antecedentes de DO. Conseguiu prever com até 72 horas a frente a concentração de OD, mas ressaltou que para um atingir um melhor desempenhó e necessária uma base de dados com mais de 1 ano de dados.…”

Section: Trabalhos Relacionadosunclassified

Modelagem e Predição temporal de Parâmetros de Qualidade de Água usando Redes Neurais Profundas

Almeida¹,

Amarís²,

Merlin³

et al. 2020

Anais Do Workshop De Computação Aplicada À Gestão Do Meio Ambiente E Recursos Naturais (WCAMA 2020)

View full text Add to dashboard Cite

A qualidade da água está diretamente relacionada com o seu nível de poluição, e para isso, é necessário o monitoramento para identificar as características físicas, químicas e biológicas, considerando a legislação vigente. Este artigo apresenta a comparação dos modelos de rede neural Long-Short Term Memory (LSTM) e Perceptron Multilayer (MLP) para predizer os parâmetros pH, OD, DBO, Fósforo e Turbidez da qualidade da água. Foram usadas as métricas de erro RMSE e MSE, quando as redes neurais são configuradas com 10, 25 e 50 neurônios. A rede LSTM apresentou um RMSE médio de 0,134, MSE médio de 0,035 e MAPE médio de 13,49. A rede MLP apresentou RMSE médio de 0,085, MSE médio de 0,01 e MAPE médio de 13,03. Os resultados do experimentos visam contribuir com o processo de monitoramento da qualidade da água e auxiliar o planejamento da gestão hídrica através do modelo de aprendizado de máquina adequado para predição dos parâmetros.

show abstract

Simultaneous modelling and forecasting of hourly dissolved oxygen concentration (DO) using radial basis function neural network (RBFNN) based approach: a case study from the Klamath River, Oregon, USA

Cited by 33 publications

References 72 publications

Dissolved oxygen concentration predictions for running waters with different land use land cover using a quantile regression forest machine learning technique

Dissolved oxygen concentration predictions for running waters with different land use land cover using a quantile regression forest machine learning technique

Incorporating Intelligence in Fish Feeding System for Dispensing Feed Based on Fish Feeding Intensity

Modelagem e Predição temporal de Parâmetros de Qualidade de Água usando Redes Neurais Profundas

Contact Info

Product

Resources

About