Forecasting of Wind- Wave Height by using Adaptive Neuro-Fuzzy Inference System and Decision Tree

Document Type: Regular Article

Authors

1 1. Graduate Master of Science of Coastal,port and marine science Engineering, Khorramshahr University of Marine Science and Technology

2 Asistant professor of River and Coastal Engineering, Khorramshahr University of Marine Science and Technology

3 4. Asistant professor of, Khorramshahr University of Marine Science and Technology

10.22115/scce.2019.199291.1125

Abstract

Wind- induced waves are considered to be the most important waves in the sea due to their high energy and frequency. Among the characteristics of the waves, height is one of the most important parameters that are used in most equations related to marine engineering designs. Since the application of soft computing methods in marine engineering has been developed in recent years, in this study, an adaptive neuro-fuzzy inference system and a decision tree have been used to predict the wind-induced wave height in Bushehr port. In order to identify the effective parameters, implementing different models from different inputs. By considering the accuracy of the models, the effective parameters in wave height were identified using statistical measures correlation coefficient (r), Mean Square Error (mse). The results of this study indicated that in the prediction of wind-induced wave height, compared to the decision tree, the accuracy of the model of the neural-fuzzy system for 3, 6 and 9 hours was higher. Also, the results showed that the use of wind shear velocity instead of wind speed at 10 meters above the water level had a higher accuracy in forecasting of the significant wave height. The results also indicated that among the presented models, the combined model of the significant wave height, shear velocity, and the difference between the direction and wind speed as well as the length of the fetch has the highest accuracy.

Keywords



Articles in Press, Accepted Manuscript
Available Online from 03 November 2019
  • Receive Date: 26 August 2019
  • Revise Date: 02 November 2019
  • Accept Date: 03 November 2019