Brazilian Forest Dataset

Dataset created to monitor the Brazilian vegetation combining 4 different systems: (i) an inventory of Brazilian seed plants created to map the country biodiversity; (ii) the Fraction of Absorbed Photosynthetically Active Radiation; (iii) the NASA Power database to include meteorological data; and (iv) the DATASUS system which makes available geographical information from Brazil. The final dataset comprises a large number of attributes including meteorological and vegetational features, which correspond to a total of 8 and 8471 attributes, respectively. Moreover, the dataset contains 20 labels and 865 geographical positions (latitude and longitude) used during the vegetation monitoring. This project makes available raw and preprocessed data, and Machine Learning models (including source codes) adjusted to : i) predict the occurrence of specific type of vegetation in different region without requiring a constant monitoring task; ii) monitor whether or not the prediction accuracy is changing after collecting new data, which provides an important tool to detect how the environment is evolving over time; and iii) study this dataset as an extra data source to better understand and simulate meteorological influences on predicted vegetation types. More information about the original datasets: (i) http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2175-78602015000401085 (ii) https://fapar.jrc.ec.europa.eu/Home.php (iii) https://power.larc.nasa.gov/ (iv) http://datasus.saude.gov.br/