The northeast region of Brazil (NEB) suffers with the worst drought during 2012-2016 that has greatly affected water availability in general, in particular the hydropower reservoirs. We have analyzed a large dataset of satellite measurements and images to understand the variability of precipitation, land surface temperature (LST) and their association with the Normalized Difference Vegetation Index (NDVI), indicator of water and vegetation stress. The drought conditions during 2012-2016 show association of poor rainfall in the year 2012, an increase of LST 7ºC above the average, reduction in NDVI upto 30% and a sharp decrease upto 28% in Relative Humidity (RH). The largest reservoir of the NEB, Sobradinho, shows decline in surface water upto about 50% which is clearly evident from the Normalized Difference Water Index (NDWI) for the period 2015-2016 compared to the year 2011.

Cartography uses large-scale digital images obtained by remote sensing. Such images are commonly used for the extraction and / or detection of cartographic features, which are the targets of interest in mapping. Extracting targets of interest from digital images streamlines the mapping, but the accuracy of this mapping depends on the characteristics of the features of interest present in the extracted image. Therefore, this paper proposes an automated way to calculate and display statistical values so that the extraction processes of any feature type mapping can be assessed considering its quality and quantity. With this purpose in mind, a computer program has been developed. This program applies an already established methodology to calculate statistical values concerning the results obtained by the automatic extraction process. The implemented program performs calculations in a quick and objective manner. In addition, it also generates resultant images that provide the user viewing of the errors obtained by the reported method. This paper presents the results obtained from the use of this computer program. Thus, the program developed accomplishes the proposed objectives, allowing the user to perform a consistent analysis of the automated extraction, since this evaluation is performed based on statistical calculations. Therefore, this program assists researchers and scholars of cartography to evaluate automatic extraction processes in the cartographic features of interest.

In the scientific literature, multiple studies address the application of road extraction methodologies to a particular cartographic dataset. However, it is difficult for any study to perform a more reliable comparison among road extraction methodologies when their results come from different cartographic datasets. Therefore, aiming to enable a more reliable comparison among different road extraction methodologies from the scientific literature, this study proposed a statistical evaluation and analysis of road extraction methodologies using a common image dataset. To achieve this goal, we setup a dataset containing remote sensing images of three different road types, highways, cities network and rural paths, and a group of images from the ISPRS (International Society for Photogrammetry and Remote Sensing) dataset. Furthermore, three road extraction methodologies were selected from the literature, in accordance with their availability, to be processed and evaluated using well-known statistical metrics. The achieved results are encouraging and indicate that the proposed statistical evaluation and analysis can allow researchers to evaluate and compare road extraction methodologies using this common dataset extracting similar characteristics to obtain a more reliable comparison among them.