Abstract
Short-term prediction of wave height is paramount in oceanic operation-related activities. Statistical models have advantages in short-term wave prediction as complex physical process is substantially simplified. However, previous statistical models have no consideration in selection of predictive variables and dealing with prediction uncertainty. This paper develops a machine learning model by combining the dynamic Bayesian network (DBN) with the information flow (IF) designated as DBN-IF. IF is focused on selecting the best predictive variables for DBN by causal analysis instead of correlation analysis. DBN for probabilistic prediction is constructed by structure learning and parameter learning with data mining. Based on causal theory, graph theory, and probability theory, the proposed DBN-IF model could deal with the uncertainty and shows great performance in significant wave height prediction compared with the artificial neural network (ANN), random forest (RF) and support vector machine (SVM) for all lead times. The interpretable DBN-IF is proven as a promising tool for nonlinear and uncertain wave height prediction.
Highlights
The intense increase in various ocean engineering has spurred an interest in accurate prediction of wave characteristics, especially significant wave height
To improve the mentioned defects in forecasting approaches, we introduce the information flow (IF) theory and dynamic Bayesian network (DBN) to propose a novel intelligent prediction model (DBN-IF) for accurate significant wave height prediction
The results reveal the effects of different predictors on prediction accuracy and consistently show the superiority of DBN-IF to other models in uncertain, nonlinear, and non-stationary wave prediction
Summary
The intense increase in various ocean engineering has spurred an interest in accurate prediction of wave characteristics, especially significant wave height. Though the relationships between wave height and relevant variables are taken into consideration in ML-based models, it is difficult to interpret those relationships using an ANN, RF, or SVM model. This problem is known as “Black Box” in neural network [27]. IF theory, put forward by Liang [28], is a novel causal analysis method He has applied causal IF to select the best predictors of tropical cyclone forecasting and compared with correlation analysis.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have