Application of Artificial Neural Network for Daily Evaporation Forecasting Using Weather Data

Abstract

Estimating evaporation is one of the most important works for meteorologists and hydrologists. This paper employed three artificial neural network (ANN) algorithms, which are linear regression (LR), multi-layer perceptron (MLP) and general regression neural network (GRNN), to investigate the possibility to apply ANNs in forecasting evaporation level. The data used in this study are observed values of meteorological variables from a weather observatory in Beijing. Temperature, air pressure and wind speed are three factors affect the level of evaporation most. The study also employed k-fold cross-validation technique to avoid overfitting and improve the performance of the models. Mean absolute error (MAE), root mean square error (MASE) and coefficient of determination (R2) statistics are used to evaluate the performance of the models and the performance of MLP is roughly same as GRNN, which is higher than LR. The result shows that ANN is a kind of accurate and reliable methods to predict evaporation.