NDVI Index Forecasting Using a Layer Recurrent Neural Network Coupled with Stepwise Regression and the PCA

ICTIC 2016 : Proceedings of the 5th Virtual International Conference of Informatics and Management Sciences, Vol.5, Iss.1 2016
Artūrs Stepčenko

In this paper predictions of the normalized difference vegetation index (NDVI) are discussed. Time series of Earth observation based estimates of vegetation inform about changes in vegetation. NDVI is an important parameter for short-term vegetation forecasting and management of various problems, such as prediction of spread of forest fire and forest disease. Artificial neural networks (ANN's) are computational models and universal approximators, which are widely used for nonlinear, non-stationary and dynamical process modeling and forecasting. In this paper, first, a stepwise regression was used as feature selection method in order to reduce input data set dimensionality and improve predictability. Correlation in input data normally creates confusion over ANN's during the learning process and thus, degrades their generalization capability. The Principal component analysis (PCA) method was proposed for elimination of correlated information in data. A layer recurrent neural network (LRN) then was used to make short-term one-step-ahead prediction of the NDVI time series.

Atslēgas vārdi
layer recurrent neural networks, normalized difference vegetation index, principal component analysis, stepwise regression
DOI
10.18638/ictic.2016.5.1.281

Stepčenko, A. NDVI Index Forecasting Using a Layer Recurrent Neural Network Coupled with Stepwise Regression and the PCA. No: ICTIC 2016 : Proceedings of the 5th Virtual International Conference of Informatics and Management Sciences, Vol.5, Iss.1, Slovākija, Zilina, 21.-25. marts, 2016. Zilina: EDIS - Publishing Institution of the University of Zilina, 2016, 130.-135.lpp. ISBN 978-80-554-1196-5. ISSN 1339-231X. e-ISSN 1339-9144. Pieejams: doi:10.18638/ictic.2016.5.1.281

Publikācijas valoda
English (en)