Application of Intelligent Dynamic Bayesian Network with Wavelet Analysis for Probabilistic Prediction of Storm Track Intensity Index

Kefeng Liu,Ming Li

doi:10.3390/atmos9060224

Abstract

The effective prediction of storm track (ST) is greatly beneficial for analyzing the development and anomalies of mid-latitude weather systems. For the non-stationarity, nonlinearity, and uncertainty of ST intensity index (STII), a new probabilistic prediction model was proposed based on dynamic Bayesian network (DBN) and wavelet analysis (WA). We introduced probability theory and graph theory for the first time to quantitatively describe the nonlinear relationship and uncertain interaction of the ST system. Then a casual prediction network (i.e., DBN) was constructed through wavelet decomposition, structural learning, parameter learning, and probabilistic inference, which was used for expression of relation among predictors and probabilistic prediction of STII. The intensity prediction of the North Pacific ST with data from 1961–2010 showed that the new model was able to give more comprehensive prediction information and higher prediction accuracy and had strong generalization ability and good stability.

Highlights

One of the primary features of mid- and high-latitude atmospheric circulation (AC) is transient variability, which is closely related to the growth and decay of daily weather systems
Lau [3] studied the seasonal variation of storm track” (ST) and pointed out that the main mode of the variation was related to the teleconnection pattern of the low-frequency circulation in the northern hemisphere
Note that time-series of the ST index is non-stationary. This limitation with non-stationary data has led to the recent formation of hybrid models, where data is preprocessed for non-stationary characteristics and run through a predicting method such as machine learning (ML) algorithms to cope with the nonlinearity

Summary

Introduction

One of the primary features of mid- and high-latitude atmospheric circulation (AC) is transient variability, which is closely related to the growth and decay of daily weather systems. In the field of meteorology and oceanology, data-driven models (i.e., statistical models) are suitable predicting tools due to their rapid development times, as well as low information requirements compared to physical-based models. Jia et al [15] applied the correlation analysis and optimal subset regression to select predictors and established a statistical prediction model for the subtropical high index. Note that time-series of the ST index is non-stationary This limitation with non-stationary data has led to the recent formation of hybrid models, where data is preprocessed for non-stationary characteristics and run through a predicting method such as ML algorithms to cope with the nonlinearity. To deal with the non-stationarity, nonlinearity, and uncertainty, we introduced DBN theory innovatively and combined WA to establish a data-driven model for predicting the monthly STII using large-scale climate indexes as the predictors. A deeper comparative analysis of model performance is conducted with key statistical indicators

Definition of Storm Track Intensity Index

Dynamic Bayesian Network Theory

Structural Learning

Node Determination—Predictor Selection

Parameter Learning

Determination of Node States

Calculation of Probability Distribution

Probabilistic Inference of Prediction Distribution

Prediction Experiment of STII

Data Introduction

Wavelet Decomposition Module

DBN Prediction Module