Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Seawalls: Performance and their failure analysis along Southern Karnataka, West Coast of India(2012) Rao, S.; Hegde, A.V.; Dwarakish, G.S.; Janardhan, J.; Venkat Reddy, D.Beach erosion is a major problem along the south west coast of India. The beach erosion particularly along the south Karnataka coast is due to, 1) direct attack of waves in an open coast, which might have been intensified in some areas due to wave refraction, 2) erosion at river mouths where one or two rivers together join the sea. The coastal protection works adopted along the South Karnataka coast are mainly the seawalls. However, some portions of these seawalls have been damaged either partially or fully. A critical study shows that these failures are due to the scouring at the toe structure. Scouring causes the failure of the seawall due to loss of support. A calculated risk may be taken to design the seawall without taking scour depth into account but provide for adequate maintenance in case scour occurs and partial failure of the seawall takes place. © 2012 Cafet-Innova Technical Society. All rights reserved.Item Hydrodynamic performance of floating kelp farms: Wave attenuation and coastal protection potential(Elsevier Ltd, 2025) Surakshitha; Rao, M.; Rao, S.Ecologically rich coastal zone play a crucial role in supporting both biodiversity and the economy. “Soft solutions” for coastal protection, such as vegetated breakwaters and artificial reefs, harness natural features to mitigate coastal erosion. Among these, flexible floating vegetation, such as kelp farms, presents a unique mechanism by altering flow patterns differently than bed-fixed vegetation. This study experimentally investigates the effectiveness of floating kelp farms in dissipating wave energy under monochromatic regular waves. The wave heights ranging from 0.06 m to 0.18 m and periods of 1.6 s–2.8 s is considered. The study examines the effects of two non-dimensional parameters: relative farm width (w/L, 0.1 to 2.5) and relative blade length (l/d, 0.25–1.0), representing the ratios of farm width to wavelength and blade length to water depth, respectively. Under the test conditions investigated, the highest wave dissipation coefficient (Kd ? 0.8) is observed for relative blade lengths of 0.75 and 0.5 at a water depth of 0.45 m. The optimal farm configuration occurred at a relative farm width between 0.3 and 0.4. These findings contribute to a better understanding of the role of kelp farm in wave energy dissipation and highlight its potential as a sustainable alternative for coastal protection. © 2025 Elsevier LtdItem 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