A study on hydrodynamics of rigid and emergent vegetated flows using machine learning approach

Maji, Soumen; Senapati, Apurbalal; Mondal, Arunendu

doi:10.1007/s11334-022-00519-6

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to overcome the above (non-linearity) problems, other methods like Polynomial Regression [11], and Piecewise Linear Regression has been used [7]. The idea behind Piecewise Linear Regression is akin to that of Linear Regression, with the key distinction being that instead of using a single line to fit the data, multiple lines are employed.…”

Section: Piecewise Linear Regressionmentioning

confidence: 99%

“…To address the aforementioned issues, alternative methods such as Polynomial Regression [11] and Piecewise Linear Regression has been employed [7]. Polynomial regression shares similarities with linear regression in that it seeks to model the relationship between an independent variable and a dependent variable.…”

Section: Related Workmentioning

confidence: 99%

“…Rather than using polynomial regression, some researchers have attempted to tackle the issue by employing piecewise linear regression [11,7]. As previously discussed 2.2, piecewise linear regression is similar to linear regression but instead involves partitioning the data based on their linear relationships and utilizing linear regression on each of the partitions.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Correlation Coefficient-based Breakpoint detection @Piecewise Linear Regression

Senapati

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Linear Regression is a traditional supervised Machine Learning technique commonly used for prediction. The approach is frequently used in many applications involving sequencing or forecasts for the time-series domain. The efficiency of the model depends on the characteristics of the data and some other external factors. One notable limitation of this model is its reliance on linear data. When presented with non-linear data, its performance can be severely impacted. To address this issue, researchers have suggested an alternative approach known as piecewise linear regression. Piecewise linear regression is a variant of linear regression that involves partitioning the data points based on their linear characteristics, followed by the application of linear regression within each partition. The primary difficulty associated with piecewise linear regression is identifying the optimal approach for partitioning the data, which can be thought of as locating the breakpoints. The main objective of this paper is to introduce a strategy for partitioning and identifying breakpoints based on the correlation properties of the data points. The effectiveness of this approach was evaluated using open-access COVID-19 data in the context of a prediction model. The findings indicate that the proposed partitioning and breakpoint identification method outperforms other existing systems, suggesting that it is a viable option that is relatively close to the optimal solution.

show abstract

Section: Piecewise Linear Regressionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Correlation Coefficient-based Breakpoint detection @Piecewise Linear Regression

Senapati

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

ML and AI-Based Prediction of Precipitation Trends

Maji,

Swargiary,

Senapati

et al. 2024

Procedia Computer Science

View full text Add to dashboard Cite

Modeling of drag coefficient under emergent and submerged flexible vegetated flow

2023

View full text Add to dashboard Cite

In an open-channel flow, vegetation study is crucial to be investigated with any type of plants including trees, shrubs, and grasses, which are growing within or near the channel banks and beds in natural or artificial waterways, such as rivers, streams, and canals. These plants are different in height, size, shape, and arrangements, which have a big impact on the turbulence and flow resistance structures. In this paper, a regression analysis has been used based on collected experimental data to improve a specific equation for the drag coefficient for rigid vegetation stems and expanded to flexible stem types under emergent and submerged flow conditions. The equation suggests a length scale metric that, by analogy with the log wake law, normalizes velocity profiles of the depth-limited open channel flow with submerged, rigid vegetation. It has been formulated by drawing regression analysis for each parameter including (Re) Reynolds number, (h*) submergence ratio, and (λ) vegetation density by considering the (Fr) Froude number ranges for the water flows and vegetated channel flows. Using the Reynolds number, which is determined by the height and diameter of the vegetation, the results demonstrate an increase and decrease in the drag coefficient. For assessing the impact of vegetation on flow resistance at the surface layer, the notion of the drag coefficient is introduced. It shows better performance than other length scales in collapsing resistance data gathered under a variety of vegetation circumstances. The proposed scaling is more accurate than those based on the logarithmic, velocity-defect, and power laws in collapsing regression analysis for the studied parameters.

show abstract

A study on hydrodynamics of rigid and emergent vegetated flows using machine learning approach

Cited by 3 publications

References 27 publications

Correlation Coefficient-based Breakpoint detection @Piecewise Linear Regression

Correlation Coefficient-based Breakpoint detection @Piecewise Linear Regression

ML and AI-Based Prediction of Precipitation Trends

Modeling of drag coefficient under emergent and submerged flexible vegetated flow

Contact Info

Product

Resources

About