Predicting the sediment rate of Nakhilo Port using artificial intelligence
In order to predict changes in coastal profile, it is necessary to investigate the sediment transport rate along the coast. Sediment transport is important in the areas of sedimentology, geomorphology, civil engineering and environmental engineering. The study of sediment transport is often performe...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iranian Association of Naval Architecture and Marine Engineering
2020-07-01
|
| Series: | International Journal of Coastal and Offshore Engineering |
| Subjects: | |
| Online Access: | http://ijcoe.org/article-1-205-en.html |
| Summary: | In order to predict changes in coastal profile, it is necessary to investigate the sediment transport rate along the coast. Sediment transport is important in the areas of sedimentology, geomorphology, civil engineering and environmental engineering. The study of sediment transport is often performed to determine the location of erosion or deposition, the amount, timing and distance of its occurrence. Forecasting future coastline changes are as a result of the marine structural development. It provides the conditions for appropriate engineering decision-making. It also makes the grounds for sustainable use of the coast. When spot and local forecasts are necessary, models based on time series like support vector regression and Artificial Neural Network as new solutions are taken into consideration. These methods are one of the ways of machine learning. This study was investigated the importance of the offshore sediment transport rate in this research for the desired beach on the west coast of Hormozgan province. The littoral drift (LITDRIFT) model is used to get this type of transfer rate. To estimate evaluation of the longshore sediment transport rate by support vector machine (SVM); it will be needed two categories of data; one for data training and the other to check the machine for testing. The results of estimation of sediment transport rate using support vector regression and artificial neural network method showed the superiority of support vector regression over the neural network in both training and experimental groups of data. |
|---|---|
| ISSN: | 2538-2667 2588-3186 |