Browsing by Author "Shankara Krishna, A."

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Assessment Of Wave Overtopping Discharge at Quarter Circle Breakwater Using Soft Computing Techniques
    (Universidad de Cantabria, 2024) Mane, V.; Shankara Krishna, A.; Rao, M.; Rao, S.
    The precise prediction of wave overtopping (WO) discharge is crucial for the design of coastal protection structures, particularly in light of the challenges posed by climate change. This study focuses on a quarter-circle breakwater (QBW) comprising a vertical back wall, a horizontal base slab on a rubble mound foundation, and a quarter-circle front wall facing incident waves. Utilizing Support Vector Machine (SVM) and Least Square Support Vector Machine (LSSVM), the research aims to estimate the mean overtopping discharge at the QBW. Input parameters, including incident wave steepness (Hi/gT2), depth parameter (d/gT2), percentage of perforations (p), and crest height parameter (Rc/Hi), are employed, with mean overtopping discharge (q/gHi T) as the output. Model performance is assessed using indicators such as Root Mean Square Error (RMSE), Correlation Coefficient (CC), Scatter Index (SI), and Index of Agreement (d). Results suggest that both SVM and LSSVM are effective in estimating mean overtopping discharge, with LSSVM demonstrating superior accuracy compared to SVM. The study findings contribute valuable insights for coastal engineering, particularly in designing structures resilient to wave overtopping amid ongoing climate change effects. © SEECMAR | All rights reserved.
  • No Thumbnail Available
    Item
    Effect of data normalisation in estimating wave overtopping discharge parameter of semicircular breakwater using ANN and Random Forest.
    (Institute of Physics, 2023) Shankara Krishna, A.; Mane, V.; Rao, S.; Rao, M.
    Breakwaters are the structures constructed in the coastal areas to maintain calm inside the port or prevent beach erosion. Semi-circular Breakwater (SCB) is an innovative type of Breakwater made of hollow caisson on a base slab with or without perforations. In this study, the wave overtopping discharge parameter of an SCB is estimated using Artificial Neural Network and Random Forest. The data is collected and used in the current research from an experimental investigation conducted in the Wave Mechanics Laboratory of the Department of Water Resources and Ocean Engineering (WROE), NITK Surathkal. Using this experimental data, the ANN and Random Forest models are developed for the prediction of the wave overtopping discharge parameter of an SCB. The performance of the models is evaluated using different statistical parameters. Data with and without normalisation are used separately to check the effect of normalisation in the prediction of wave overtopping discharge parameter using ANN and Random Forest. From the results, it is found that ANN gives better results when the data is normalised. The performance of Random Forest is independent of the data normalisation. © Published under licence by IOP Publishing Ltd.
  • No Thumbnail Available
    Item
    Predicting wave reflection coefficient of vertical caisson breakwater using machine learning: A data-driven approach
    (Elsevier Ltd, 2025) Shankara Krishna, A.; Rao, M.; Rao, S.
    Coastal zones are vital for ecological balance and human development, but are increasingly threatened by wave activity, shoreline erosion, and sea-level rise. To mitigate these challenges, engineers employ coastal protection structures. Specifically, vertical caisson breakwaters are preferred in deeper waters due to their advantages. Reflection Coefficient is an important hydrodynamic performance indicator for breakwaters. Recently, machine learning (ML) has been used for predicting coastal engineering parameters, offering an efficient means to support or augment traditional physical model studies, particularly during preliminary design phases, if sufficient quality data is available. This research focuses on using ML models to estimate the reflection coefficient of vertical caisson breakwaters based on a limited set of experimental data. Four different algorithms- Artificial Neural Network (ANN), Random Forest (RF), Gradient Boosting (GB), and Extreme Gradient Boosting (XGB)- are developed and evaluated. Hyperparameters are optimised using a hybrid approach, combining Grid Search with manual refinement. Of the four models, XGB achieved the highest prediction accuracy (Test CC = 0.9631), while Random Forest exhibited the smallest generalisation gap, indicating strong consistency across datasets. The findings from the study suggest that XGB offers an efficient tool for early-stage design applications in coastal engineering. © 2025 Elsevier Ltd