Data mining for meteorological applications: Decision trees for modeling rainfall prediction

Abstract

Prediction is a challenging task and that too for weather is even more complex, dynamic and mind-boggling. Weather prediction poses right from the ancient times as a big herculean task, because it depends on various parameters to predict the dependent variables like temperature, rainfall, humidity, wind speed and direction, which are changing from time to time and weather calculation varies with the geographical location along with its atmospheric variables. There are many data mining techniques employed for weather prediction, but decision tree evaluation can be quantified. This paper highlights a model using decision tree to predict weather phenomena like fog, rainfall, cyclones and thunderstorms, which can be a life saving information and used by peoples of all walks of life in making wise and intelligent decisions. This model may be used in machine learning and further promises the scope for improvement as more and more relevant attributes can be used in predicting the dependent variables. The proposed model is implemented using the open source data mining tool Rapidminer.