Monthly flow forecast for Mississippi River basin using artificial neural networks

2013 ◽  
Vol 24 (7-8) ◽  
pp. 1785-1793 ◽  
Author(s):  
C. Sivapragasam ◽  
S. Vanitha ◽  
Nitin Muttil ◽  
K. Suganya ◽  
S. Suji ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Mississippi River ◽  
Mississippi River Basin ◽  
Artificial Neural ◽  
Flow Forecast

Large-scale Groundwater Simulation using Artificial Neural Networks in the Danube River Basin

2020 ◽  
Author(s):  
Illias Landros ◽  
Ioannis Trichakis ◽  
Emmanouil Varouchakis ◽  
George P. Karatzas
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Danube River ◽  
Bayesian Regularization ◽  
Data Set ◽  
The Danube River ◽  
Precipitation Temperature ◽  
Artificial Neural ◽  
Danube River Basin

<p>In recent years, Artificial Neural Networks (ANNs) have proven their merit in being able to simulate the changes in groundwater levels, using as inputs other parameters of the water budget, e.g. precipitation, temperature, etc.. In this study, ANNs have been used to simulate hydraulic head in a large number of wells throughout the Danube River Basin, taking as inputs, precipitation, temperature, and evapotranspiration data in the region. Different ANN architectures have been examined, to minimize the simulation error of the testing data-set. Among the different training algorithms, Levenberg-Marquardt and Bayesian Regularization are used to train the ANNs, while the different activation functions of the neurons that were deployed include tangent sigmoid, logarithmic sigmoid and linear. The initial application comprised of data from 128 wells between 1 January 2000 and 31 October 2014. The best performance was achieved by the algorithm Bayesian Regularization with a error of the order  based on all observation wells. A second application, compared the results of the first one, with the results of an ANN used to simulate a single well. The pros and cons of the two approaches, and the synergies of using both of them is further discussed in order to distinguish the differences, and guide researchers in the field for further applications.</p>

scholarly journals DESENVOLVIMENTO DE REDES NEURAIS ARTIFICIAIS PARA ESTIMATIVA DAS VAZÕES DIÁRIAS NA BACIA DO RIO PIRACICABA5

Irriga ◽  
2018 ◽  
Vol 23 (4) ◽  
pp. 756-772
Author(s):  
Eduardo Morgan Uliana ◽  
Demetrius David da Silva ◽  
Michel Castro Moreira ◽  
Donizete Dos Reis Pereira ◽  
Silvio Bueno Pereira ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Hydrologic Modeling ◽  
Minas Gerais ◽  
Mato Grosso ◽  
Artificial Neural ◽  
E Mail ◽  
Daily Flows ◽  
Piracicaba River

DESENVOLVIMENTO DE REDES NEURAIS ARTIFICIAIS PARA ESTIMATIVA DAS VAZÕES DIÁRIAS NA BACIA DO RIO PIRACICABA5     EDUARDO MORGAN ULIANA1; DEMETRIUS DAVID DA SILVA2; MICHEL CASTRO MOREIRA3; DONIZETE DOS REIS PEREIRA4; SILVIO BUENO PEREIRA2 E FREDERICO TERRA DE ALMEIDA1   1Universidade Federal de Mato Grosso (UFMT), Instituto de Ciências Agrárias e Ambientais (ICAA), Avenida Alexandre Ferronato, CEP.: 78557-267, Sinop – MT, Brasil, e-mail: [email protected], [email protected]. 2Universidade Federal de Viçosa (UFV), Departamento de Engenharia Agrícola, Avenida Peter Henry Rolfs, CEP.: 36570-900, Viçosa – MG, Brasil, e-mail: [email protected]. 3Universidade Federal do Oeste da Bahia, Centro das Ciências Exatas e das Tecnologias, Rua Professor José Seabra de Lemos, CEP.: 47808-021, Barreiras – BA, Brasil, e-mail: [email protected]. 4Universidade Federal de Viçosa (UFV), Instituto de Ciências Agrárias, Rodovia LMG 818, km 06, Florestal – MG, Brasil, e-mail: [email protected]. 5O artigo é referente ao capítulo 3 da tese de doutorado do primeiro autor.     1 RESUMO   As Redes Neurais Artificiais (RNAs) são uma alternativa na modelagem hidrológica para a estimativa das vazões dos cursos de água a partir de dados hidrometeorológicos. O objetivo do trabalho foi desenvolver Redes Neurais Artificiais para estimar as vazões diárias na bacia hidrográfica do rio Piracicaba, Minas Gerais. O estudo foi realizado em três seções de monitoramento de vazão da bacia do rio Piracicaba, localizada no Estado de Minas Gerais - Brasil. No desenvolvimento das RNAs foram realizados a coleta e seleção dos dados; a definição da arquitetura da rede; e o treinamento e validação das redes desenvolvidas. A maior parte das RNAs desenvolvidas apresentou coeficiente de Nash-Sutcliffe maior que 0,80 o que permitiu classificar os modelos como bons para a estimativa das vazões. Com base nos resultados, pode-se concluir que as RNAs são adequadas para a estimativa das vazões diárias na bacia do rio Piracicaba e podem ser empregadas na estimativa de eventos extremos e no gerenciamento dos recursos hídricos.   Palavras-Chave: modelo empírico inteligência artificial, modelagem hidrológica.     ULIANA, E. M.; SILVA, D. D.; MOREIRA, M. C.; PEREIRA, D. R.; PEREIRA, S. B.; ALMEIDA, F. T. ARTIFICIAL NEURAL NETWORKS FOR DAILY FLOW ESTIMATES IN THE PIRACICABA RIVER BASIN     2 ABSTRACT   Artificial neural networks (ANNs) have been used alternatively in hydrologic modeling to estimate accurately watercourse flows based on hydrometeorological data. This study developed artificial neural networks to estimate daily flows in Piracicaba river basin, in Minas Gerais state (Brazil). For this, we used three runoff-monitoring sections of the Piracicaba river basin, with an area of 5,304.0 km2, and located in the State of Minas Gerais – Brazil. For designing the ANNs to estimate daily flows, we adopted the following steps: data collection and selection, network architecture definition, training and validation of results. The results showed that ANNs are adequate to estimate daily flows in Piracicaba river basin.   Keywords: empirical model, artificial intelligence, hydrologic modeling.

Turbidity Prediction in a River Basin by Using Artificial Neural Networks: A Case Study in Northern Spain

2013 ◽  
Vol 28 (2) ◽  
pp. 319-331 ◽  
Author(s):  
C. Iglesias ◽  
J. Martínez Torres ◽  
P. J. García Nieto ◽  
J. R. Alonso Fernández ◽  
C. Díaz Muñiz ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Northern Spain ◽  
Artificial Neural

scholarly journals Discharge Forecasting By Applying Artificial Neural Networks At The Jinsha River Basin, China

2016 ◽  
Vol 12 (9) ◽  
pp. 108 ◽  
Author(s):  
Muhammad Tayyab ◽  
Jianzhong Zhou ◽  
Xiaofan Zeng ◽  
Rana Adnan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Back Propagation ◽  
Research Area ◽  
Ar Model ◽  
Jinsha River ◽  
Flood Prediction ◽  
Linear Pattern ◽  
Artificial Neural

Flood prediction methods play an important role in providing early warnings to government offices. The ability to predict future river flows helps people anticipate and plan for upcoming flooding, preventing deaths and decreasing property destruction. Different hydrological models supporting these predictions have different characteristics, driven by available data and the research area. This study applied three different types of Artificial Neural Networks (ANN) and an autoregressive model to study the Jinsha river basin (JRB), in the upper part of the Yangtze River in China. The three ANN techniques include feedforward back propagation neural networks (FFBPNN), generalized regression neural networks (GRNN), and the radial basis function neural networks (RBFNN). Artificial Neural Networks (ANN) has shown Great deal of accuracy as compared to statistical autoregressive (AR) model because statistical model cannot able to simulate the non-linear pattern. The results varied across the cases used in the study; based on available data and the study area, FFBPNN showed the best applicability, compared to other techniques.

Sign in / Sign up

Export Citation Format

Share Document