Simulations of runoff and evapotranspiration in Chinese fir plantation ecosystems using artificial neural networks

Abstract

Runoff and evapotranspiration are two key variables of water budget in forest ecosystems. Modeling runoff and evapotranspiration dynamics play a vital role in assessing the hydrology cycle and function of forest ecosystems. Based on the hydrological and meteorological data collected over 20 years from January of 1988 to December of 2007 at Huitong National Forest Ecosystem Research Station, we used back propagation neural network (BPNN) and genetic neural network (GNN) models to simulate runoff and evapotranspiration of Chinese fir plantations for two watersheds located in Huitong county of Hunan Province, China. The purpose of this study was to accurately simulate runoff and evapotranspiration dynamics using both BPNN and GNN models. The model simulations of the runoff and evapotranspiration indicated that the GNN model concurrently possesses efficiency, effectiveness, and robustness. Moreover, the simulated results of GNN and BPNN model were compared with a multivariate statistics (M-slat) model. We found that the GNN model performed better than M-slat and BPNN models for modeling both runoff and evapotranspiration of Chinese fir plantations in China.