scholarly journals Application of gradient tree boosting regressor for the prediction of scour depth around bridge piers

2021 ◽  
Author(s):  
B. M. Sreedhara ◽  
Amit Prakash Patil ◽  
Jagalingam Pushparaj ◽  
Geetha Kuntoji ◽  
Sujay Raghavendra Naganna
Keyword(s):  
Model Performance ◽  
Bridge Piers ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Scour Depth ◽  
Clear Water ◽  
Sediment Size ◽  
Learning Techniques ◽  
Scour Hazard ◽  
Bed Scour

Abstract Scour around bridge piers is a complex phenomenon and it is essential to assess or predict the scour hazard around bridge piers in tandem with completely understanding its mechanism. To date, there is no exact method for the estimation of scour depth. Nowadays, machine learning techniques are being recognized as effective tools for the prediction of scour depth using experimental data. In the present study, gradient tree boosting (GTB) technique was used for the prediction of scour depth around various pier shapes under different streambed conditions. Sediment size, sediment quantity, velocity, and flow time were used as input parameters to predict the scour depth under clear-water and live-bed scour conditions. The scour depth was predicted for different pier shapes such as, circular, rectangular, round-nosed and sharp-nosed shaped. The GTB model predicted scour depth values were compared with that of the group method of data handling (GMDH) technique. The performance of GTB and GMDH models were then evaluated based on statistical indices such as RRMSE, NNSE, WI, MNE, SI, and KGE. The study concludes that the GTB model performance was relatively superior to that of GMDH in the prediction of scour depth around different pier shapes.

Abutment scour in clear-water and live-bed conditions by GMDH network

2013 ◽  
Vol 67 (5) ◽  
pp. 1121-1128 ◽  
Author(s):  
Mohammad Najafzadeh ◽  
Gholam-Abbas Barani ◽  
Masoud Reza Hessami Kermani
Keyword(s):  
Back Propagation ◽  
Support Vector ◽  
Group Method ◽  
Scour Depth ◽  
Back Propagation Algorithm ◽  
Clear Water ◽  
Sediment Size ◽  
Svm Model ◽  
Vector Machines ◽  
Abutment Scour

In the present study, the Group Method of Data Handling (GMDH) network has been utilized to predict abutments scour depth for both clear-water and live-bed conditions. The GMDH network was developed using a Back Propagation algorithm (BP). Input parameters that were considered as effective variables on abutment scour depth included properties of sediment size, geometry of bridge abutments, and properties of approaching flow. Training and testing performances of the GMDH network were carried out using dimensionless parameters that were collected from the literature. The testing results were compared with those obtained using the Support Vector Machines (SVM) model and the traditional equations. The GMDH network predicted the abutment scour depth with lower error (RMSE (root mean square error) = 0.29 and MAPE (mean absolute percentage of error) = 0.99) and higher (R = 0.98) accuracy than those performed using the SVM model and the traditional equations.

Clear-water scour at bridge piers in fine and medium gravel beds

2005 ◽  
Vol 32 (4) ◽  
pp. 775-781 ◽  
Author(s):  
Rajkumar V Raikar ◽  
Subhasish Dey
Keyword(s):  
Bridge Piers ◽  
Geometric Standard Deviation ◽  
Scour Depth ◽  
Size Factor ◽  
Clear Water ◽  
Envelope Curve ◽  
Gravel Beds ◽  
Sediment Size ◽  
Gravel Size ◽  
Equilibrium Scour Depth

An experimental investigation on scour at circular and square piers in uniform and non-uniform gravels (fine and medium sizes) under clear-water scour at limiting stability of gravels is presented. From the experimental results, it is observed that the equilibrium scour depth increases with decrease in gravel size. The variation of equilibrium scour depth with gravel sizes departures considerably from that with sand sizes. Consequently, the resulting sediment size factors for gravels, obtained from envelope curve fitting, are significantly different from the existing sediment size factor for sands. The influence of gravel gradation on scour depth is also prominent in non-uniform gravels. The time scales to represent the time variation of scour depth in uniform and non-uniform gravels are determined. For uniform gravels, the non-dimensional time scale increases with increase in pier Froude number and gravel size, whereas for non-uniform gravels, it decreases with increase in geometric standard deviation of particle size distribution of gravels.Key words: bridge pier, gravel beds, scour, erosion, sediment transport, open channel flow, hydraulic engineering.

Evaluation of Selected Pier-Scour Equations Using Field Data

1996 ◽  
Vol 1523 (1) ◽  
pp. 186-195 ◽  
Author(s):  
Mark N. Landers ◽  
David S. Mueller
Keyword(s):  
Field Measurements ◽  
Bridge Piers ◽  
Critical Ratio ◽  
Scour Depth ◽  
Flow Depth ◽  
Clear Water ◽  
Pier Scour ◽  
Logarithmic Space ◽  
State Highway ◽  
Federal Highway

Field measurements of channel scour at bridges are needed to improve the understanding of scour processes and the ability to accurately predict scour depths. An extensive data base of pier-scour measurements has been developed over the last several years in cooperative studies between state highway departments, the Federal Highway Administration, and the U.S. Geological Survey. Selected scour processes and scour design equations are evaluated using 139 measurements of local scour in live-bed and clear-water conditions. Pier-scour measurements were made at 44 bridges around 90 bridge piers in 12 states. The influence of pier width on scour depth is linear in logarithmic space. The maximum observed ratio of pier width to scour depth is 2.1 for piers aligned to the flow. Flow depth and scour depth were found to have a relation that is linear in logarithmic space and that is not bounded by some critical ratio of flow depth to pier width. Comparisons of computed and observed scour depths indicate that none of the selected equations accurately estimate the depth of scour for all of the measured conditions. Some of the equations performed well as conservative design equations; however, they overpredict many observed scour depths by large amounts. Some equations fit the data well for observed scour depths less than about 3 m (9.8 ft), but significantly underpredict larger observed scour depths.

scholarly journals Nose-Angle Bridge Piers as Alternative Countermeasures for Local Scour Reduction

2018 ◽  
Vol 13 (2) ◽  
pp. 110-120 ◽  
Author(s):  
Ibtesam Abudallah Habib ◽  
Wan Hanna Melini Wan Mohtar ◽  
Atef Elsaiad ◽  
Ahmed El-Shafie
Keyword(s):  
Froude Number ◽  
Local Scour ◽  
Bridge Piers ◽  
Scour Depth ◽  
Skew Angle ◽  
Flow Angle ◽  
Sediment Size ◽  
Low Froude Number ◽  
Skew Angles ◽  
Depth Reduction

This study investigates the performance nose-angle piers as countermeasures for local scour reduction around piers. Four nose angles were studied, i.e., 90°, 70°, 60° and 45° and tested in a laboratory. The sediment size was fixed at 0.39 mm whereas the flow angle of attack (or skew angle) was varied at four angles, i.e., skew angles, i.e., 0°, 10°, 20° and 30°. Scour reduction was clear when decreasing nose angles and reached maximum when the nose angle is 45°. Increasing the flow velocity and skew angle was subsequently increasing the scour profile, both in vertical and transversal directions. However, the efficiency of nose angle piers was only high at low Froude number less than 0.40 where higher Froude number gives minimal changes in the maximum scour depth reduction. At a higher skew angle, although showed promising maximum scour depth reduction, the increasing pier projected width resulted in the increase of transversal lengths.

Clear-water local scour at wide piers in shallow-water flow

2014 ◽  
Vol 9 (3) ◽  
pp. 331-343 ◽  
Author(s):  
N. Ahmad ◽  
T. Mohamed ◽  
F. H. Ali ◽  
B. Yusuf
Keyword(s):  
Laboratory Data ◽  
Local Scour ◽  
The Other ◽  
Scour Depth ◽  
Temporal Development ◽  
Clear Water ◽  
Shallow Water Flow ◽  
Equilibrium Time ◽  
Sediment Size ◽  
Flow Intensity

Laboratory data for local scour depth regarding the size of wide piers are presented. Clear water scour tests were performed for various pier widths (0.06, 0.076, 0.102, 0.14 and 0.165 m), two types of pier shapes (circular and rectangular) and two types of uniform cohesionless bed sediment (d50 = 0.23 and d50 = 0.80 mm). New data are presented and used to demonstrate the effects of pier width, pier shape and sediment size on scour depth. The influence of equilibrium time (te) on scouring processes is also discussed. Equilibrium scour depths were found to decrease with increasing values of b/d50. The temporal development of equilibrium local scour depth with new laboratory data is demonstrated for flow intensity V/Vc = 0.95. On the other hand, the results of scour mechanism have shown a significant relationship between normalized volume of scoured and deposited with pier width, b. The experimental data obtained in this study and data available from the literature for wide piers are used to evaluate predictions of existing methods.

Machine Learning Techniques to Predict Software Defect

2014 ◽  
pp. 1422-1434 ◽  
Author(s):  
Ramakanta Mohanty ◽  
Vadlamani Ravi
Keyword(s):  
Machine Learning ◽  
Feature Subset Selection ◽  
Machine Learning Techniques ◽  
Group Method ◽  
Software Project ◽  
Feature Subset ◽  
Software Defects ◽  
Software Defect ◽  
Learning Techniques ◽  
Sensitivity Specificity

The past 10 years have seen the prediction of software defects proposed by many researchers using various metrics based on measurable aspects of source code entities (e.g. methods, classes, files or modules) and the social structure of software project in an effort to predict the software defects. However, these metrics could not predict very high accuracies in terms of sensitivity, specificity and accuracy. In this chapter, we propose the use of machine learning techniques to predict software defects. The effectiveness of all these techniques is demonstrated on ten datasets taken from literature. Based on an experiment, it is observed that PNN outperformed all other techniques in terms of accuracy and sensitivity in all the software defects datasets followed by CART and Group Method of data handling. We also performed feature selection by t-statistics based approach for selecting feature subsets across different folds for a given technique and followed by the feature subset selection. By taking the most important variables, we invoked the classifiers again and observed that PNN outperformed other classifiers in terms of sensitivity and accuracy. Moreover, the set of ‘if- then rules yielded by J48 and CART can be used as an expert system for prediction of software defects.

Local scour at piled bridge piers including an examination of the superposition method

2014 ◽  
Vol 41 (5) ◽  
pp. 461-471 ◽  
Author(s):  
Ata Amini ◽  
Bruce W. Melville ◽  
Thamer M. Ali
Keyword(s):  
Bridge Piers ◽  
Prediction Methods ◽  
Scour Depth ◽  
Superposition Method ◽  
Clear Water ◽  
Laboratory Flume ◽  
Pile Cap ◽  
The Individual ◽  
Comparison Of The Results ◽  
Bed Material

An experimental investigation of clear water scour at complex piers is presented. Five complex piers, comprising different configurations of piles, pile cap, and column, were tested in a laboratory flume using uniform bed material. The piers were tested for a range of possible elevations relative to the streambed elevation. Experiments were undertaken using the complex piers and also using the individual components of each complex pier. A comparison of the results for the intact piers and for their components enabled an evaluation of the prediction methods involving superposition of scour depths at piles, pile cap, and pier column. The superposition method is found to give inadequate estimates of total scour depth in many cases.

Group method of data handling to predict scour depth around bridge piers

2012 ◽  
Vol 23 (7-8) ◽  
pp. 2107-2112 ◽  
Author(s):  
Mohammad Najafzadeh ◽  
Hazi Mohammad Azamathulla
Keyword(s):  
Bridge Piers ◽  
Group Method ◽  
Scour Depth ◽  
Data Handling

scholarly journals Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective

2021 ◽  
Vol 8 ◽  
Author(s):  
Daniele Roberto Giacobbe ◽  
Alessio Signori ◽  
Filippo Del Puente ◽  
Sara Mora ◽  
Luca Carmisciano ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Prediction Models ◽  
Early Recognition ◽  
Model Performance ◽  
Daily Practice ◽  
Machine Learning Techniques ◽  
Medical Decision ◽  
Long Run ◽  
Learning Techniques

Sepsis is a major cause of death worldwide. Over the past years, prediction of clinically relevant events through machine learning models has gained particular attention. In the present perspective, we provide a brief, clinician-oriented vision on the following relevant aspects concerning the use of machine learning predictive models for the early detection of sepsis in the daily practice: (i) the controversy of sepsis definition and its influence on the development of prediction models; (ii) the choice and availability of input features; (iii) the measure of the model performance, the output, and their usefulness in the clinical practice. The increasing involvement of artificial intelligence and machine learning in health care cannot be disregarded, despite important pitfalls that should be always carefully taken into consideration. In the long run, a rigorous multidisciplinary approach to enrich our understanding in the application of machine learning techniques for the early recognition of sepsis may show potential to augment medical decision-making when facing this heterogeneous and complex syndrome.

Experimental Study on Clear Water Scour around Bridge Piers

2011 ◽  
Vol 121-126 ◽  
pp. 162-166
Author(s):  
Yao Ming Hong ◽  
Min Li Chang ◽  
Hsueh Chun Lin ◽  
Yao Chiang Kan ◽  
Chi Chang Lin
Keyword(s):  
Flow Velocity ◽  
Large Diameter ◽  
Bridge Piers ◽  
Scour Depth ◽  
Clear Water ◽  
Experimental Conditions ◽  
Cover Depth ◽  
Sediment Cover ◽  
Equilibrium Scour Depth ◽  
Fast Flow

This study analyzed the characteristics of bridge scoured by clear water according to 14 groups of laboratory experiments. The formulation of critical velocity based on historical equations of clear water scour was concluded for the test circumstances in laboratory. The experimental conditions include the variation of flow velocity, sediment cover depth, and diameter of bridge pier/bases. The erosion status prior to the maximum scour depth was recorded by a pinhole camera, and, in general, the equilibrium scour depth was reached after 24 hours. The maximum scour depth increases as the sand cover depth decreases. As the same sediment depth, the fast flow velocity will induce the deep scour depth with respect to the slow flow velocity. The same result can be observed for the large diameter of pier (or base) versus the small one. The maximum scour depths in the front of the pier are always deeper than that behind the pier.

Sign in / Sign up

Export Citation Format

Share Document