The Estimation of Wind Velocity Using Data Mining Techniques

Abstract

Estimation of wind velocity in real time is very essential as it can provide valuable information to people of different domains such as agriculture, aviation and tourism to mention few. Since climate data is growing exponentially it is hard to analyze it manually. Therefore, machine-learning techniques such as unsupervised and supervised learning methods are used to mine voluminous data and discover valuable knowledge. Predictive modeling in data mining is required to estimate climate parameters. In this paper, we proposed a framework that exploits data mining techniques such as J48, KNN, Neural Networks, SVM and Linear Regression. The framework takes climate dataset as input, completes training phase and makes different models using data mining algorithms. Finally, it ends by exploiting linear regression, which models the relationship between a dependent variable and an exploratory variable. The framework results in estimating wind velocity and finding prediction error rate. A prototype application is built based on Weka, which is used to demonstrate proof of the concept. The empirical results applied on all data are obtained from the Turkish Government Meteorology Services for summer months of 2013. It  revealed that the proposed framework is useful to have a predictive model with respect to estimation of climate parameters.