Short-term forecasting of soil temperature using artificial neural network

摘要: Soil temperature is one of the most important meteorological parameters that plays a critical role in land surface hydrological processes. In current study, artificial neural network (ANN) models were developed and tested for 1 day ahead soil forecasting at 5, 10, 20, 30, 50 100 cm depths. Antecedent temperatures plus concurrent antecedent air used as inputs ANN models. data collected from two Iranian weather stations located humid arid regions period 2004-2005. The models' accuracies evaluated using Nash-Sutcliffe co-efficient efficiency, correlation co-efficient, root mean square error bias between observed forecasted values. efficiency values >0.94 >0.96 all show can be applied successfully to provide accurate reliable short-term forecasts.