Estimating Evapotranspiration Using Artificial Neural Network and Minimum Climatological Data

Zanetti, Sandra Aparecida Serra; Sousa, Elias Fernandes de; Oliveira, V. P. S.; Almeida, Frederico Terra de; Bernardo, Salassier

doi:10.1061/(asce)0733-9437(2007)133:2(83)

Cited by 190 publications

(106 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Visando selecionar uma RNA que proporcionasse o melhor desempenho, efetuou-se um estudo prévio no qual se realizaram vários testes, variando-se o número de camadas ocultas, o número de neurônios e a função de ativação em cada camada; para cada combinação dessas características a rede foi treinada e testada (Zanetti et al, 2007;2008), o que possibilitou a escolha da melhor RNA para estimar o coeficiente de rugosidade. A camada de saída da rede foi predefinida com apenas um neurônio e função de ativação do tipo linear.…”

Section: Modelagem Do Coeficiente De Rugosidade Por Redes Neurais Artunclassified

Coeficiente de rugosidade de Manning para o rio Paracatu

Lyra¹,

Cecílio

Zanetti

et al. 2010

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

RESUMOPela teoria do escoamento em canais abertos, o coeficiente de rugosidade de Manning é um dos principais parâmetros para descrição da vazão sobre uma superfície. Uma das dificuldades da aplicação da equação de Manning é a definição do seu coeficiente de rugosidade em rios e canais, razão pela qual o presente estudo tem como objetivo, estimar o coeficiente de rugosidade de Manning para os períodos de vazão mínima e máxima média mensal, em alguns trechos do rio Paracatu, e propor um modelo baseado em redes neurais artificiais para estimar o coeficiente de rugosidade. O coeficiente foi determinado em função das características geométricas do canal (área molhada, raio hidráulico e declividade do canal) e das séries de vazão de seis postos fluviométricos do rio Paracatu. Utilizaram-se séries de vazão de 21 anos . O coeficiente de rugosidade não apresenta tendência (maior ou menor) em função apenas do período seco ou de cheia. As características da margem e do leito do rio influenciam diretamente nos valores de coeficiente de rugosidade. O modelo baseado em rede neural apresentou desempenho satisfatório, o que possibilita estimar o coeficiente de rugosidade em função da cota, vazão, declividade e do raio hidráulico do rio. Palavras-chave: vazão, condutos livres, redes neurais artificiaisManning roughness coefficient for Paracatu river, Brazil ABSTRACTAccording to open channel draining theory, the Manning's roughness coefficient is one of most important parameters to describe surface flow. One of the difficulties in applications of Manning's equation is the definition of its roughness coefficient in rivers and channels. Thus, the aims of this paper are to estimate the Manning's roughness coefficient for the periods of minimum and maximum mean monthly flow in some parts of Paracatu river and to propose a model based on artificial neural networks to estimate the roughness coefficient. The coefficient was determined in function of channel geometrical characteristics (wetted area, hydraulic radius and slope of the channel) and of the outflow series of six fluviometric stations of Paracatu river. Long-term series of 21 years (1976 -1996) of outflow were used. The roughness coefficient does not show any tendency (up or down)as a function of the dry or overflow periods only. The characteristics of margin and watercourse of river influenced directly the roughness coefficient data. The model based on neural network showed satisfactory performance, which allow us to estimate the roughness coefficient as a function of the quota, slope and hydraulic radius of the river.

show abstract

Section: Modelagem Do Coeficiente De Rugosidade Por Redes Neurais Artunclassified

Coeficiente de rugosidade de Manning para o rio Paracatu

Lyra¹,

Cecílio

Zanetti

et al. 2010

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

show abstract

“…JST ini telah banyak digunakan dalam ilmu hidrologi untuk memrediksi arus sungai (Partal, 2009;Phukoetphim et al, 2014;Tiwari et al, 2012;Vafakhah, 2012), memrediksi curah hujan (Arif et al, 2012), evapotranspirasi (Adamala et al, 2014;Jahanbani, dan El-Shafie, 2011;Zanetti et al, 2007), banjir secara real time (Ghalkhani et al, 2013), dan banjir regional (Aziz et al, 2014) serta memrediksi kualitas air sungai (Asadollahfardi, et al, 2012;Huang dan Liu, 2010). Model yang dihasilkan oleh mereka rata-rata memberikan nilai efisiensi dan korelasi tinggi, misalnya yang dihasilkan oleh Tiwari et al (2012) memberikan nilai efisiensi 85%, atau Partal (2009) memberikan koefisien korelasi 0,90.…”

Section: Metode Penelitianunclassified

Prediction of water discharge and sediment in teak forested area using artificial neural network model

Wahyuningrum¹

2017

JPKW

View full text Add to dashboard Cite

Informasi tentang hubungan curah hujan, debit aliran dan sedimen diperlukan dalam perencanaan pengelolaan DAS. Hubungan ini dikenal sangat nonlinear dan kompleks. Meskipun debit dan sedimen sudah dimonitor secara terus menerus, namun kadang kala informasinya tidak atau kurang lengkap. Dalam kondisi ini pemodelan sangat diperlukan. Tujuan penelitian adalah membuat model untuk memrediksi hasil air (direct runoff) dan sedimen bulanan dengan menggunakan Jaringan Syaraf Tiruan (JST). Model yang diuji menggunakan data hujan pada saat t-3 dan t-4 sebagai input, dan debit dan sedimen pada t+3 dan t+4 sebagai output. Data yang digunakan merupakan data tahun 2001 sampai dengan tahun 2014. Hasil penelitian menunjukkan bahwa dari beberapa model yang diuji terdapat 2 model untuk prediksi debit dan 2 model untuk prediksi sedimen. Model tersebut terpilih karena mempunyai MSE terkecil, R 2 terbesar dan K yang memuaskan (0,65). Dengan demikian, model-model tersebut dapat digunakan untuk memrediksi debit dan sedimen untuk jangka t+3 dan t+4. Prediksi debit t+3 dan t+4 dapat menggunakan persamaan berturut-turut Q t+3 = 0,64 Q t-3 + 0,05 dan Q t+4 = 0,65 Q t-4 + 0,074, sedangkan prediksi sedimen t+3 dan t+4 menggunakan persamaan QS t+3 = 0,45 QS t-3 + 0,052 dan QS t+4 = 0,45 QS t-4 + 0,052. Pemodelan dengan JST ini dapat diaplikasikan untuk memrediksi debit dan sedimen di lokasi yang lain dengan arsitektur yang disesuaikan dengan kondisi data yang tersedia. ABSTRACT Information on the relationship of rainfall with discharge and sediment are required in watershed management.This relationship is known to be highly nonlinear and complex. Although discharge and sediment has been monitored continuously, but sometimes the information is not or less complete. In this condition, modeling is indispensable.The research objective is to create a model to predict the monthly direct runoff and sediment using Artificial Neural Network (ANN).The model was tested using rainfall data at t-3 and t-4 as input, and discharge and sediment at t+3 and t+4 as output. The data used is the data from 2001 to 2014. The resultsshowed that of some models tested there are two models for the prediction of discharge and two models for sediment.The model was chosen because it has the smallest MSE, the largest R 2 and satisfying K (0.5 to 0.65

show abstract

“…The similarity effect of input nodes is thus eliminated (Kim et al, 2009). According to Zanetti et al (2007), by grouping the daily values into averages, ET o may be calculated due to their highest stabilization. For data normalization, the data of input and output nodes were scaled in the range of [0 1] using the following equation (11).…”

Section: Data Normalizationmentioning

confidence: 99%

Development of Hybrid Method for the Modeling of Evaporation and Evapotranspiration

Kim¹

2012

Evapotranspiration - Remote Sensing and Modeling

View full text Add to dashboard Cite

Estimating Evapotranspiration Using Artificial Neural Network and Minimum Climatological Data

Cited by 190 publications

References 8 publications

Coeficiente de rugosidade de Manning para o rio Paracatu

Coeficiente de rugosidade de Manning para o rio Paracatu

Prediction of water discharge and sediment in teak forested area using artificial neural network model

Development of Hybrid Method for the Modeling of Evaporation and Evapotranspiration

Contact Info

Product

Resources

About