Clustering Methods to Asses Land Cover Samples of MODIS Vegetation Indexes Time Series

MODIS vegetation indexes time series have been widely used to build land cover change maps on large scales. In this scope, to obtain good quality maps using supervised classification methods, it is crucial to select representative training samples of land cover change classes. In this paper, we evaluate two clustering methods, Hierarchical and Self-Organizing Map (SOM), to assess land cover samples of MODIS vegetation indexes time series. As we show, these techniques are suitable tools for assisting users to select representative land cover change samples from MODIS vegetation indexes time series. We present the accuracy of both methods for a case study in Ipiranga do Norte municipality in Mato Grosso state, Brazil.

[1]  Tatiana V. Tatarinova,et al.  Nonlinear Mixture Models: A Bayesian Approach , 2014 .

[2]  Hans-Hermann Bock,et al.  Information and Entropy in Cluster Analysis , 1994 .

[3]  Damien Arvor,et al.  Analyzing the agricultural transition in Mato Grosso, Brazil, using satellite-derived indices , 2012 .

[4]  Raul Zurita-Milla,et al.  Self-organizing maps as an approach to exploring spatiotemporal diffusion patterns , 2013, International Journal of Health Geographics.

[5]  Olatz Arbelaitz,et al.  An extensive comparative study of cluster validity indices , 2013, Pattern Recognit..

[6]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[7]  Milos Radovanovic,et al.  Clustering Evaluation in High-Dimensional Data , 2019, EDML@SDM.

[8]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[9]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[10]  Jiyuan Liu,et al.  Land cover characterization of Temperate East Asia using multi-temporal VEGETATION sensor data , 2004 .

[11]  A. Huete,et al.  A comparison of vegetation indices over a global set of TM images for EOS-MODIS , 1997 .

[12]  Daniel Alves Aguiar,et al.  Modis time series to assess pasture land , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[13]  Jianwen Ma,et al.  Land cover classification from MODIS EVI times-series data using SOM neural network , 2005 .

[14]  S. Frolking,et al.  Sensitivity of vegetation indices to atmospheric aerosols: Continental-scale observations in Northern Asia , 2003 .

[15]  W. Natita,et al.  Appropriate Learning Rate and Neighborhood Function of Self-organizing Map (SOM) for Specific Humidity Pattern Classification over Southern Thailand , 2016 .

[16]  Gilberto Câmara,et al.  A Time-Weighted Dynamic Time Warping Method for Land-Use and Land-Cover Mapping , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.