Author:

Keywords:

Soil temperature, ANN, Forecasting, Science & Technology, Physical Sciences, Meteorology & Atmospheric Sciences, daily soil temperature, soil depth, air temperature, time series forecasting, multilayer perceptron, RAINFALL-RUNOFF PROCESS, PREDICTION, MODEL, ALGORITHMS, ISSUES, 0401 Atmospheric Sciences, 3701 Atmospheric sciences, 3702 Climate change science

Abstract:

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