Abstract
This study evaluates the predictive modeling of the daily ambient temperature (maximum, T(max); average, T(ave); and minimum, T(min)) and its hourly estimation (T(0h), …, T(23h)) using artificial neural networks (ANNs) for agricultural applications. The data, 2004-2010, were used for training and 2011 for validation, recorded at the SIAR agrometeorological station of Mansilla Mayor (León). ANN models for daily prediction have three neurons in the output layer (T(max)(t + 1), T(ave)(t + 1), T(min)(t + 1)). Two models were evaluated: (1) with three entries (T(max)(t), T(ave)(t), T(min)(t)), and (2) adding the day of the year (J(t)). The inclusion of J(t) improves the predictions, with an RMSE for T(max) = 2.56, T(ave) = 1.65 and T(min) = 2.09 (°C), achieving better results than the classical statistical methods (typical year T(ave) = 3.64 °C; weighted moving mean T(max) = 2.76, T(ave) = 1.81 and T(min) = 2.52 (°C); linear regression T(ave) = 1.85 °C; and Fourier T(max) = 3.75, T(ave) = 2.67 and T(min) = 3.34 (°C)) for one year. The ANN models for hourly estimation have 24 neurons in the output layer (T(0h(t)), …, T(23h(t))) corresponding to the mean hourly temperature. In this case, the inclusion of the day of the year (J(t)) does not significantly improve the estimations, with an RMSE = 1.25 °C, but it improves the results of the ASHRAE method, which obtains an RMSE = 2.36 °C for one week. The results obtained, with lower prediction errors than those achieved with the classical methods, confirm the interest in using the ANN models for predicting temperatures in agricultural applications.