ANN approaches for the prediction of bridge backwater using both field and experimental data

Pinar, Engin; Seçkin, Galip; Şahi̇n, Beşi̇r; Akıllı, Hüseyin; Çobaner, Murat; Canpolat, Çetin; Atabay, Serter; Kocaman, Selahattin

doi:10.1080/15715124.2011.553833

Cited by 5 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a rise in water surface level may be caused due to 6 bridge constriction during flood events. In Figure 1, dh denotes bridge backwater, and According to previous studies [3,[8][9][10]31], four parameters have the most significant impacts on bridge backwater. These parameters are 1…”

Section: Bridge Backwater Problemsmentioning

confidence: 95%

“…Likewise, the data considered in this study comprises both experimental and field data sets. [3,10,18], it is technically reliable for developing accuracy-improved equations for estimating bridge backwater.…”

Section: Bridge Backwater Databasementioning

confidence: 99%

“…First of all, the considered database was randomly divided into the train and test data [21]. Since a generic equation is sought for bridge backwater, both experimental and field data are treated the same in this data-splitting process, as those conducted in the relevant studies [3][4]10]. As previously mentioned, the utilized database has 202 and 66 laboratory and field data, respectively.…”

Section: Train and Test Datamentioning

confidence: 99%

“…From the type of bridge, they may be grouped as contributions focusing on bridges with either horizontal soffit [1] or arch deck [2][3][4]. From methodological point of view, some researches applied numerical [5][6], experimental [7][8], and data mining approaches [3,[9][10][11] to predict bridge backwater. Furthermore, it should be noted that most of methods estimating bridge afflux have been basically developed based on field or laboratory datasets.…”

Section: Introductionmentioning

confidence: 99%

“…In this regard, the limitations of the available explicit equations for predicting backwater depth include (1) they were not developed by powerful algorithms and (2) their accuracy is not enough to be applied in professional software for analyzing rivers and designing of hydraulic structures. In order to enhance the accuracy of backwater estimation, artificial intelligence (AI) models including radial basis function based neural network (RBNN), multi-layer perceptron (MLP), generalized regression neural networks (GRNN), and adaptive neuro-fuzzy inference system (ANFIS) have been utilized for this purpose using experimental and field databases [3][4][10][11]. In spite of all these studies, an accurate explicit equation, which takes all involving variables into account and developed by powerful algorithms like GA, has not been proposed based on the current literature.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Bridge backwater estimation: A Comparison between artificial intelligence models and explicit equations

2020

View full text Add to dashboard Cite

Estimation of bridge backwater has been one of practical challenges in hydraulic engineering for decades. In this study, Genetic Programming (GP) has been applied for estimating bridge backwater for the first time based on the conducted literature review. Furthermore, two new explicit equations are developed for predicting bridge afflux using Genetic Algorithm (GA) and hybrid MHBMO-GRG algorithm. The performances of these models are compared with Artificial Neural Network (ANN) and several explicit equations available in the literature considering both laboratory and field data. Based on five considered performance evaluation criteria, the two new explicit equations outperform the ones available in the literature. Furthermore, GP and ANN achieve the 2 best results in favor of four out of five considered criteria for train and test data, respectively. To be more specific, ANN improves the MSE and R 2 values of the explicit equation developed using GA by 44% and 12% for the test data while GP enhances the corresponding values by 62% and 9% for the train data. Finally, the results demonstrate that not only artificial intelligence models considerably improve bridge afflux estimation than the explicit equations but also the suggested equations significantly improve the accuracy of the available explicit ones.

show abstract