Analysis and data mining of orbital sensor data for monitoring sugarcane crops

• Bruno F. Amaral USP
• Daniel Y. Chino USP
• Luciana A. S. Romani Embrapa
• Renata R. V. Gonçalves Unicamp
• Elaine P. M. de Sousa USP
• Agma J. M. Traina USP

Abstract

Researches aiming greenhouse gases reduction have been motivated by the impact of extreme climate events around the world. In Brazil, sugar cane is the main source for ethanol production to replace fossil fuels. In this context, remote sensing imagery has been widely used to monitor sugar cane harvests and to support scientific research. In this paper, we propose a methodology based on data clustering to analyze NDVI time series obtained from AVHRR/NOAA satellites and monitor the growing cycles of sugar cane crops. The experiments show that our approach can identify areas with similar development patterns also considering different growing crops seasons.

References

Berndt, D. and Clifford, J. (1994) “Using dynamic time warping to find patterns in time series”. In: AAAI Workshop on Knowledge Discovery in Databases, p. 359-370, Seattle - Washington.

Chino, D. Y. T., Romani, L. A. S. e Traina, A. J. M. (2010) “Construindo séries temporais de imagens de satélite para sumarização de dados climáticos e monitoramento de safras agrícolas”. In: REIC, v. 10, p. 1-16.

Ding, H., Trajcevski, G., Scheuermann, P., Wang, X. and Keogh, E. (2008). “Querying and Mining of Time Series Data: Experimental Comparison of Representations and Distance Measures”. In: VLDB Endowment, p. 1542-1552.

IPCC (2007) “Climate change 2007: Fourth assessment report (AR4)”. In: Intergovernmental Panel on Climate Change.

Han, J., Kamber, M. and Tung, A. K. H. (2001) “Spatial Clustering Methods in Data Mining: A Survey”. In: Geographic Data Mining and Knowledge Discovery, Edited by H. J. Miller and J. Han, Taylor and Francis, p. 201-230.

Romani, L. A. S., Gonçalves, R. R. V., Amaral, B. F., Zullo Jr, J., Traina Jr, C., Sousa, E. P. e Traina, A. J. M. (2011) “Acompanhamento de safras de cana-de-açúcar por meio de técnicas de agrupamento em séries temporais de NDVI”. In: XV Simpósio Brasileiro de Sensoriamento Remoto, Curitiba - PR, p. 383-390.