Carlos Viegas Damásio
Carlos Viegas Damásio is Associate Professor at Departamento de Informática da Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa working currently on applications of AI-based techniques to agriculture and forestry. He got a B.Sc. in Informatics Engineering in 1992 and a Ph.D. in Computer Science in 1996 by Universidade Nova de Lisboa. He (co)supervised 2 PhD students, and more than 30 MSc. students. He led 2 research projects, and participated in more than 10 other research projects. He published more than 100 papers in conferences and journals on topics of Logic Programming, Non-Monotonic Reasoning, Semantic Web, Knowledge Representation, Agroinformatics, Remote Sensing, Machine Learning, Model Based Diagnosis, and Paraconsistency and Uncertainty. He regularly serves as PC member of the top conferences of his area. Recently, he has been defining new models and techniques for acquiring and processing remote and field data for agricultural and forestry applications, for the constructing pest and disease models crops from satellite and weather station data. In parallel, he is working on formal models of data provenance for expressive query languages that allow tracking the dependencies of answers on raw data as well as the operations applied to derive them. He is the Principal Investigator of Floresta Limpa (PCIF/MOG/0161/2019), where the team is constructing a system deployed in the Cloud to monitor wildfire fuel breaks surrounding roads, houses, and localities, applying machine learning to remote sensing data, combining with a Volunteer Geographic Information mobile App to acquire ground-truth and correct it. In project SmartFarm (POCI-010247-FEDER-046078), he led the NOVALINCS team to construct new applications for sustainable agriculture, where deep learning techniques have been used to identify weeds from photos, count insects in traps, and count fruits from videos. In project FitoAgro (PDR2020-101-031686) he led the NOVALINCS team, where a system was constructed to help agronomists in obtaining curated field-data for pest control.