Zinātniskās darbības atbalsta sistēma
Latviešu English

Publikācija: Normalized Difference Vegetation Index Forecasting Using a Regularized Layer Recurrent Neural Network

Publikācijas veids Citas publikācijas konferenču (arī vietējo) ziņojumu izdevumos
Pamatdarbībai piesaistītais finansējums Nav zināms
Aizstāvēšana: ,
Publikācijas valoda English (en)
Nosaukums oriģinālvalodā Normalized Difference Vegetation Index Forecasting Using a Regularized Layer Recurrent Neural Network
Pētniecības nozare 2. Inženierzinātnes un tehnoloģijas
Pētniecības apakšnozare 2.2. Elektrotehnika, elektronika, informācijas un komunikāciju tehnoloģijas
Autori Artūrs Stepčenko
Atslēgas vārdi layer recurrent neural networks, normalized difference vegetation index, time series forecasting
Anotācija 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 vegetation forecasting and management of various problems, such as climate change monitoring, energy usage monitoring, managing the consumption of natural resources, agricultural productivity monitoring, drought monitoring and forest fire detection. 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. A layer recurrent neural network (LRN) is used in this paper to make one-step-ahead prediction of the NDVI time series.
DOI: 10.18638/quaesti.2015.3.1.192
Atsauce Stepčenko, A. Normalized Difference Vegetation Index Forecasting Using a Regularized Layer Recurrent Neural Network. No: QUAESTI 2015 : Proceedings of the 3rd Virtual Multidisciplinary Conference QUAESTI, Vol.3, iss.1, Slovākija, Zilina, 7.-11. decembris, 2015. Zilina: EDIS - Publishing Institution of the University of Zilina, 2015, 261.-266.lpp. ISBN 978-80-554-1170-5. ISSN 2453-7144. e-ISSN 1339-5572. Pieejams: doi:10.18638/quaesti.2015.3.1.192
Pilnais teksts Pilnais teksts
Publikācijas versija
Licence
ID 22050