Preprint Article Version 1 NOT YET PEER-REVIEWED

Triplet Markov Chain for Modeling a Non-Stationary NDVI Time Series

  1. National School of Computer Science, SIVIT-RIADI Laboratory, University of Manouba, Manouba 2010, Tunisia
  2. LIMOS Laboratory, University of Blaise Pascal, 63170 Aubière, France
  3. ITI Department, Telecom Bretagne, Technopôle Brest-Iroise - CS 83818, 29238 BREST CEDEX 3, France
Version 1 : Received: 1 August 2016 / Approved: 2 August 2016 / Online: 2 August 2016 (05:21:17 CEST)

How to cite: Ben Abbes, A.; Farah, I.; Barra, V. Triplet Markov Chain for Modeling a Non-Stationary NDVI Time Series. Preprints 2016, 2016080009 (doi: 10.20944/preprints201608.0009.v1). Ben Abbes, A.; Farah, I.; Barra, V. Triplet Markov Chain for Modeling a Non-Stationary NDVI Time Series. Preprints 2016, 2016080009 (doi: 10.20944/preprints201608.0009.v1).

Abstract

In this paper, we propose a Triplet Markov Chain (TMC) based technique to study vegetation monitoring using remotely sensed data. TMCs are a generalization of Hidden Markov Model (HMM). This latter has proved its ability to represent multi-temporal satellite images as well as to analyze vegetation dynamics on large scales. The main idea of using HMM is to relate the varying spectral response along the crop cycle with plant life. However, there has been considerable dissatisfaction, because it has been found unable to study a non-stationary data. An interesting feature for the application of TMC is to use auxiliary processes which model the non-stationarity. The primary purpose of this paper is to present a novel methodology based on TMC for modeling a non-stationary Normalized Difference Vegetation Index (NDVI) time series. In order to assess the performance of the proposed model experiments are carried out using Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI time series of the northwestern region of Tunisia. Moreover, the developed model is compared to two models HMM and Seasonal Auto Regressive Integrated Moving Average (SARIMA). Our results show the efficacy of our model with a precision of 82.36%.

Subject Areas

NDVI time series; vegetation; HMM; non-stationary; TMC

Readers' Comments and Ratings (0)

Discuss and rate this article
Views 260
Downloads 245
Comments 0
Metrics 0
Discuss and rate this article

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.