Forest coverage prediction based on least squares support vector regression algorithm is presented in the paper.Forest coverage data of Heilongjiang from 1994 to 2005 are used to study the effectiveness of least squares support vector regression algorithm.The prediction results of the proposed least squares support vector regression model by using the training samples with the different dimensional input vector are given in the study. It can be seen that the prediction results of the proposed least squares support vector regression model by using the training samples with the 3-dimensional input vector have best prediction results.The comparison of forest coverage forecasting error between the proposed least squares support vector regression model and the support vector regression model is given, among which mean prediction error of the proposed least squares support vector regression model is 0.0149 and mean prediction error of the support vector regression model is 0.0322 respectively.The experimental results show that the proposed least squares support vector regression model has more excellent forest coverage forecasting results than the support vector regression model.
A hybrid slantlet denoising least squares support vector regression model for exchange rate prediction
