Are the temperature of indian cities increasing? : Some insights using change point analysis with functional data

Abstract

In recent years there has been considerable concern expressed worldwide re- garding increase in temperature popularly called the global warming problem. In this paper we examine monthly temperature data of nine Indian cities for the period 1961 to 2013. We introduce a new Gaussian process based method for change point detection with functional data and use it to investigate the existence of change point for the temperature data series of nine Indian cities. It is found that there has been a rise in the average temperature for eight of the nine cities during this period. The magnitude of warming is found not to be uniform but vary across cities located in different parts of India. The cities located in hilly areas is seen to have warmed more than those located in the plains. The estimated change points for the eight cities are not identical but most of them are in the period 1994 - 2001. The fndings suggest that imme- diate policy measures are required to ensure that no further warming happens in these cities.