Soil Temperature Prediction Using Time-Delay Neural Networks
Neural networks are widely used for time series prediction in the recent years. In particular, dynamic neural networks with embedded time delays are the most appropriate models for the simulation of nonlinear processes since they make use the effect of past input values. The purpose of this study is to predict soil temperature in various depths, by using dynamic neural networks. The dynamic networks used are recurrent neural networks with feedback loop that includes time-delay elements. The data used for the neural network’s training, validation and testing were hourly values obtained from the weather station at the Agricultural University of Athens, for the period 2002–2005. Error statistics of the results showed a good fitting of the models.
KeywordsSoil Temperature Mean Square Error Recurrent Neural Network Recurrent Network Neural Network Toolbox
- AbdAlKader SA, AL-Allaf ONA (2011) Backpropagation neural network algorithm for forecasting soil temperatures considering many aspects: a comparison of different approaches. In: Proceedings of the 5th international conference on information technology, Amman, 11–13 May 2011Google Scholar
- Beale MH, Hagan MT, Demuth HB (2011) Neural network toolbox getting started guide R2011b. http://mathworks.com/help/pdf_doc/nnet/nnet_gs.pdf. Accessed on 25 November 2011
- Diamantopoulou MJ, Georgiou PE, Papamichail DM (2010) Performance evaluation of artificial neural networks in estimating reference evapotranspiration with minimal meteorological data. Global NEST J 13:18–27Google Scholar
- Veronez MR, Thum AB, Luz AS, da Silva DR (2006) Artificial neural networks applied in the determination of soil surface temperatures – SST. In: Proceedings of 7th international symposium on spatial accuracy assessment in nature resources and environmental sciences, LisbonGoogle Scholar