ImpactU Versión 3.11.2 Última actualización: Interfaz de Usuario: 16/10/2025 Base de Datos: 29/08/2025 Hecho en Colombia
Protocolo de procesamiento de imágenes satelitales para el entrenamiento y prueba de una red neuronal de predicción de daño ecológico por extracción ilegal de minerales dentro del marco de celebración de los 100 años de la Fuerza Aérea Colombiana
Giving scope to the objectives and commitments assumed by the Francisco José de Caldas District University at the head of the GITEM ++ Telemedicine Research Group, within the framework of the Inter-Institutional Cooperation Agreement between the Colombian Air Force (FAC) and the District University, the following research project - innovation in commemoration of the 100 years of the FAC and whose purpose focuses on the definition of a protocol processing geospatial data for training and testing a prediction model ecological damage caused by illegal mining open sky based on computational intelligence techniques. For the above, different physical and socioeconomic factors that intervene in the ecological damage were identified and some decision rules on land cover behaviors were stipulated for the determination of this effect on the territory, later variables were established that reflected said factors, these being obtainable from the treatment and processing of aerospace information and its interrelation with qualitative social and economic data. In order to reach this processing, several experimental tests were carried out in order to determine the best algorithms for extracting useful information, mainly from satellite images. Finally, the previous findings were synthesized in a processing protocol that allowed feeding a neural network for the prediction of ecological damage by illegal mining.