Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item In order to study sediment travelling paths across shoreline in different seasons, sediment samples were collected normal to the shoreline along three profiles, separated by 220m from Surathkal beach near Karnataka Regional Engineering College (K.R.E.C.), Karnataka. The sediments were analysed for their grain size characteristics (statistical parameters) and sediment trend matrix was prepared. By using sediment trend matrix, sediment travelling paths were drawn. It has been found that during premonsoon, sediments were moving predominantly towards offshore region, resulting in erosion. Sediments were moving predominantly towards shore and build-up of beach takes place during the post monsoon season.(Sediment trend matrix analysis along shore normal transects off Surathkal beach, Karnataka) Rao, S.; Shirlal, K.G.; Rao, N.B.S.2003Item Prediction of wind-wave climate along Karnataka coast(Springer, 2021) Upadhyaya, K.S.; Rao, S.; Rao, M.Karnataka is a coastal state on the west coast of India along the Arabian Sea. The coast experiences a harsh wave climate during the southwest monsoons. Most of the coast is facing problems due to coastal erosion. Hence, in the present study, a numerical model has been set up using MIKE 21 Spectral Wave (SW) module to predict the wave climate. The wave climate along the Indian domain is simulated by wind speed datasets from Global Climate Model (GCM). Wind speed datasets from ERA-Interim is initially validated against in-situ measurement which had a correlation of 0.93. A hindcast study spanning 26 years based on 38 GCMs from different modelling institutes was performed. A comparison of wind speed datasets showed CMCC-CM RCP 4.5 wind projections were closer to ERA-Interim reanalyzed dataset and was used to predict the wave climate. The performance of the MIKE numerical model driven by CMCC-CM RCP 4.5 wind fields showed a correlation greater than 0.7 when validated against in-situ measurement. The numerical model simulations driven by wind speeds from CMCC-CM RCP 4.5 up to the year 2070 showed a gradual increase in the significant wave height which is indicative of the effects of climate change on the wave climate along the Karnataka coast. The projected significant wave height for 2070, when compared with the present wave climate, indicated an increase in the range of 10–21% at the six locations. The predicted wave pattern based on numerical simulations indicated a shift in the peak values in the monsoon month of June along the coast. The predicted wave parameters with a 10-year return period can be used for the design of coastal structures along the Karnataka coast. © 2021, Indian Academy of Sciences.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