FORECAST OF METEOROLOGICAL PARAMETERS, USING DATA MINING. A PRACTICAL CASE

Abstract

This work focuses on the problem of forecasting meteorological parameters such as temperature, relative humidity, solar radiation, dew point and rainfall, from a set of data obtained from a weather station. To solve this problem, data mining techniques have been used, including M5Rules, M5P, Linear Regression and Nearest Neighbour. As a result of the work, it is shown that the M5Rules technique is appropriate for the forecast of temperature, relative humidity, as well as for dew point, while the nearest neighbour technique is more appropriate for forecasting solar radiation and rainfall.