Computational framework to analyze agrometeorological, climate and remote sensing data: challenges and perspectives
L. A. S. Romani, Agma J. M. Traina, Elaine Parros Machado de Sousa, Jurandir Zullo, Ana Maria Heuminski de Ávila, Jose Fernando Rodrigues Junior, Caetano Traina · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · 2009
Abstract. In the past few years, improvements in the data acquisition technol-ogy have decreased the time interval of data gathering. Consequently, institu-tions have stored huge amounts of data such as climate time series and remote sensing images. Computational models to filter, transform, merge and analyze data from many different areas are complex and challenging. The complexity in-creases even more when combining several knowledge domains. Examples are research in climatic changes, biofuel production and environmental problems. A possible solution to the problem is the association of several computational techniques. Accordingly, this paper presents a framework to analyze, moni-tor and visualize climate and remote sensing data by employing methods based on fractal theory, data mining and visualization techniques. Initial experiments showed that the information and knowledge discovered from this framework can be employed to monitor sugar cane crops, helping agricultural entrepreneurs to make decisions in order to become more productive. Sugar cane is the main source to ethanol production in Brazil, and has a strategic importance for the country economy and to guarantee the Brazilian self-sufficiency in this impor-tant, renewable source of energy. 1.