Applications of SVM networks in hybrid model for environment parameters estimation

Abstract

Weather forecast is a valuable practical problem and has important implications for agriculture, industry and other services. There have been different proposed methods to forecast the weather parameters [3, 6, 8, 9], but the parameters of the prediction model depends on the geographical conditions and the economic development of the given area. Therefore, for every new location, we need to redefine the parameters of the model or to propose a more suitable model. This paper proposes to use an artificial neural network SVM (Support Vector Machine) in a hybrid model [2] to predict the maximum and minimum temperature of the day. The input data is the historical values of maximum and minimum temperatures, humidity, wind speed and average values of rainfall, sun hours for past days. Model inputs are evaluated and selected using linear decomposition coefficients estimated using SVD (Singular Value Decomposition). The quality of the proposed solution is tested on real 2191 days data from the province of Hai Duong.