Annotating data to support decision-making: a case study

Georeferenced data are a key factor in many decision-making systems. However, their interpretation is user and context dependent so that, for each situation, data analysts have to interpret them, a time-consuming task. One approach to alleviate this task, is the use of semantic annotations to store the produced information. Annotating data is however hard to perform and prone to errors, especially when executed manually. This difficulty increases with the amount of data to annotate. Moreover, annotation requires multidisciplinary collaboration of researchers, with access to heterogeneous and distributed data sources and scientific computations. This paper illustrates our solution to approach this problem by means of a case study in agriculture. It shows how our implementation of a framework to automate the annotation of geospatial data can be used to process real data from remote sensing images and other official Brazilian data sources.