The group Hakuna Datata, formed by students of the Master's Degree in Big Data Science of the University of Navarra, has won the first phase of the challenge 'Minsait Land Classification' of the Cajamar University Hack 2020 Datathon and will represent the University in the national phase. This is the III edition of the contest, organized by Cajamar Data Lab, which is aimed at students from the best training centers in science of data in Spain.

The challenge 'Minsait Land Classification' sought that students develop the best automatic land classification model based on the images provided by the Sentinel II satellite of the Copernicus service of the European Space Agency. Using R and Python programs and machine learning techniques, they had to classify a set of cadastral farms associated with a list of attributes extracted from the image.

To this end, the students first performed a cleaning and enrichment of the data, which allowed them to achieve a high correspondence with reality. Then, they performed a modeling of the data with the Gradiant Boosting and Random Forest binary classification models.

The Hakuna Datata team is formed by Pablo Jordán de la source, Gabriel López Font and Manuel Alberto Mosquera Belfort. During this second phase, which ends on April 22, they will be able to improve their work on the same datasets and with the same goal.

The Master's Degree University in Big Data Science at the University of Navarra is coordinated this year by the Institute for Culture and Society (ICS) and, starting next year, by the Institute of Science of the data and Artificial Intelligence, attached to TECNUN School of Engineering.