Wave height prediction using the rough set theory

Integrated interdisciplinary modeling techniques, providing reliable and accurate estimates for wave characteristics, have gained attention in recent years. With the ability to express knowledge in a rule-based form, the Rough Set Theory (RST) has been successfully employed in many fields. However the application of RST has not been investigated in wave height (WH) prediction. In this paper, the RST is applied to Lake Superior in North America to find some simple rules, called decision rules, for WH prediction. Decision rules are derived by expressing WH as functions of wind data gathered by the National Data Buoy Center (NDBC). Comparing results of RST with results of other soft computing techniques such as Support Vector Machines (SVMs), Bayesian Networks (BNs), Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) indicates that the RST outperforms other soft computing techniques in WH prediction and provide some simple decision rules which can be accurately used by decision makers and engineers.

► In this paper, a new Rough Set Theory-based methodology is proposed for wave height prediction.
► The Rough Set Theory is applied to Lake Superior to find some rules for Wave Height prediction.
► The results show that the Rough Set Theory outperforms other soft computing techniques.
► The methodology provides some decision rules which can be accurately used by decision makers.