Classification Analysis of NDVI Time Series in Metric Spaces for Sugarcane Identification

Lucas Felipe Kunze, Thábata Amaral, Leonardo Mauro Pereira Moraes, Jadson José Monteiro Oliveira, Altamir Gomes Bispo Junior, Elaine Parros Machado de Sousa, Robson Leonardo Ferreira Cordeiro

2018

Abstract

In Brazil, agribusiness is an important task to the economy, since it provides a substantial part of the country's Gross Domestic Product (GDP). Besides that, interest in biofuels has grown, considering that they viabilize the use of renewable energy. Brazil is the world's largest producer of sugarcane, which enables a large ethanol production. Thus, to monitor agricultural areas is important to support decision making. However, the amount of generated and stored data about these areas has been increasing in such a way that far exceeds the human capacity to manually analyze and extract information from it. That is why automatic and scalable data mining approaches are necessary. This work focuses on the sugarcane classification task, taking as input NDVI time series extracted from remote sensing images. Existing related works propose to analyze non-metric features spaces using the DTW distance function as a basis. Here we demonstrate that analyzing the multidimensional space with Minkowski distance provides better results, considering a variety of classifiers. XGBoost and kNN, both using L2 distance, performed similarly or better than the DTW-based classifiers in terms of accuracy

Paper Citation

in Harvard Style

Kunze L., Amaral T., Mauro Pereira Moraes L., José Monteiro Oliveira J., Gomes Bispo Junior A., Parros Machado de Sousa E. and Cordeiro R. (2018). Classification Analysis of NDVI Time Series in Metric Spaces for Sugarcane Identification.In Proceedings of the 20th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-298-1, pages 162-169. DOI: 10.5220/0006709401620169

in Bibtex Style

@conference{iceis18,
author={Lucas Felipe Kunze and Thábata Amaral and Leonardo Mauro Pereira Moraes and Jadson José Monteiro Oliveira and Altamir Gomes Bispo Junior and Elaine Parros Machado de Sousa and Robson Leonardo Ferreira Cordeiro},
title={Classification Analysis of NDVI Time Series in Metric Spaces for Sugarcane Identification},
booktitle={Proceedings of the 20th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2018},
pages={162-169},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006709401620169},
isbn={978-989-758-298-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Classification Analysis of NDVI Time Series in Metric Spaces for Sugarcane Identification
SN - 978-989-758-298-1
AU - Kunze L.
AU - Amaral T.
AU - Mauro Pereira Moraes L.
AU - José Monteiro Oliveira J.
AU - Gomes Bispo Junior A.
AU - Parros Machado de Sousa E.
AU - Cordeiro R.
PY - 2018
SP - 162
EP - 169
DO - 10.5220/0006709401620169