An improved random forest algorithm and its application to wind pressure prediction

When making regression predictions, the traditional random forest (RF) algorithm can only make predictions within the training set, which can easily lead to overfitting when modeling data have some specific noise. To solve the problem of over-fitting, an improved RF method is proposed in this paper for wind pressure prediction. With the aim to verify the prediction performance of the improved RF algorithm, this paper predicts the wind pressure coefficients of a high-rise building model without wind pressure measurement points. The results show that the improved RF can achieve good results in predicting the mean and fluctuating wind pressure coefficients of high-rise buildings, and its relative error for each measurement point is basically controlled at 5%, which is acceptable in engineering terms. Further applications show that this improved RF can be used for wind pressure distribution prediction in other large-span building type wind tunnel tests.