Multiple Change-point Estimator For Meteorological Data Based On ASAMC Algorithm

The research of change point has obtained more and more attention in meteorology and finance fields. We can use the method of detecting change point to determine whether or not structural change happened to the data sequence of precipitation, pressure,humidity and temperature by analysis or observe the meteorology data. It is very important in meteorology analysis.In chapter 1, we present a brief introduction of the derivation of change point; then we discuss the different expressions and common research methods of change point in different fields; In the end, the current research methods in single change point and multiple change point are mentioned.In chapter 2, we emphasize the theory of Bayesian estimation, Monte Carlomethods, M-H Algorithm, and SAMC Algorithm, give a brief introduction of ASAMC model. The last of the chapter is the procedure of ASAMC.In chapter 3, we discuss the structural change of mean annual temperatures and mean monthly temperatures from 1955 to 2010 by ASAMC. At the situation of that we assume that the average temperature is normal distribution, we use the Bayesian method to establish the multiple change-point model of the average temperature series. The results show that ASAMC algorithm can effectively find out the number and the positions of the change points, and the change points detected by the monthly average temperature data sequence is more accurate than by the annual average temperature data sequence.In chapter 4, there is a conclusion of this paper, at the same time, deficiencies and prospects are given.