Applying Markov Chains for NDVI Time Series Forecasting of Latvian Regions

Arthur Stepchenko, Jurij Chizhov


Time series of earth observation based estimates of vegetation inform about variations in vegetation at the scale of Latvia. A vegetation index is an indicator that describes the amount of chlorophyll (the green mass) and shows the relative density and health of vegetation. NDVI index is an important variable 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. In this paper, we make a one-step-ahead prediction of 7-daily time series of NDVI index using Markov chains. The choice of a Markov chain is due to the fact that a Markov chain is a sequence of random variables where each variable is located in some state. And a Markov chain contains probabilities of moving from one state to other.


Forecasting; Markov chains; NDVI

Full Text:



M. M. Badamasi, S. A. Yelwa, M. A. AbdulRahim and S. S. Noma, “NDVI threshold classification and change detection of vegetation cover at the Falgore Game Reserve in Kano State, Nigeria,” Sokoto Journal of the Social Sciences, vol. 2, no. 2, pp. 174–194.

N. B. Duy and T. T. H. Giang, “Study on vegetation indices selection and changing detection thresholds selection in Land cover change detection assessment using change vector analysis,” presented at International Environmental Modelling and Software Society (iEMSs), Sixth Biennial Meeting, Leipzig, Germany, 2012.

E. Sahebjalal and K. Dashtekian, “Analysis of land use-land covers changes using normalized difference vegetation index (NDVI) differencing and classification methods,” African J. of Agricultural Research, vol. 8, no. 37, pp. 4614-4622, September 26, 2013.

M. Manobavan, N. S. Lucas, D. S. Boyd and N. Petford, “Forecasting the interannual trends in terrestrial vegetation dynamics using time series modelling techniques,” presented at the ForestSAT Symposium Heriot Watt University, Edinburgh, United Kingdom, 5th - 9th August 2002.

University of Natural Resources and Life Sciences, Vienna. Data service platform for MODIS Vegetation Indices time series processing at BOKU, Vienna. Available:, [Accessed August 25, 2015].

F. Vuolo, M. Mattiuzzi, A. Klisch and C. Atzberger, “Data service platform for MODIS Vegetation Indices time series processing at BOKU Vienna: current status and future perspectives,” Proc. SPIE 8538, Earth Resources and Environmental Remote Sensing/GIS Applications III, 85380A (October 25, 2012).

R. M. Feldman and C. Valdez-Flores, Applied Probability and Stochastic Processes, 2nd Edition, Springer-Verlag Berlin Heidelberg 2010, p. 141.

D. R Anderson, D. J. Sweeney, T. A. Williams, J. D. Camm and J. J. Cochran, Quantitative Methods for Business, 13th Edition, South- Western College Pub 2015, p. 771.

T. Liu, “Application of Markov Chains to Analyze and Predict the Time Series,” Modern Applied Science, vol. 4, no. 5, pp. 162-166, May 2010.

V. Soloviev, V. Saptsin and D. Chabenko, “Markov Chains Application To The Financial-Economic Time Series Prediction,” Computer Modelling and New Technologies, vol. 14, no. 3, pp. 16–20, 2011.

G. Rakocevic, T. Djukic, N. Filipovic and V. Milutinovic, Computational Medicine in Data Mining and Modeling, Springer-Verlag New York 2013, p. 205.

B. Liu, Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data, 2nd Edition, Springer-Verlag Berlin Heidelberg 2011, p. 280.


  • There are currently no refbacks.

Copyright (c) 2015 Arthur Stepchenko, Jurij Chizhov

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.