I am Adjunct Professor (UHD1, tenure tracker) at the University of Twente, faculty of Geo-Information Science and Earth Observation (ITC), department of Earth Observation Science (EOS), Enschede, The Netherlands.

Before joining ITC, I was a Marie Curie research fellow with the project “MaleRS - Machine learning techniques for the analysis and classification of the last generation of remote sensing data”, supported by the European Commission and the Province of Trento. During the first two years of this project, I conducted my research activity at the Department of Empirical Inference, Max Planck Institute for Intelligent Systems, Tubingen, Germany. From June 2013 to August 2014, I was with the Remote Sensing Laboratory, Department of Information Engineering and Computer Science, University of Trento.

My main research interests are on the analysis of remote sensing data, machine learning, image classification, and pattern recognition.

Check my Google Scholar citations here.

Honours and awards

My research interest is about ‘Deep Learning for Earth Observation.’ I investigate deep learning methods for various types of remotely sensed data and geospatial applications. My aim is to develop novel methods and systems designed according to the characteristics of the Earth observation data, the geospatial application domain and the requirements of users and stakeholders. With a problem-solving attitude, methodologies are designed around societally and environmentally relevant problems. Technological constraints and data availability requirements are also taken into account. Education and institutional strengthening activities benefit from the knowledge and expertise gained through such research, generating, in turn, additional insight into user needs and open problems.

The ambition to pursue innovative research in the growing and competitive field of deep learning for Earth observation requires passion, creative thinking, and a solid understanding of remote sensing data and geospatial applications. My approach to achieving this vision is to:

• design deep learning solutions according to the characteristics of the remotely sensed data (RGB, multispectral, hyperspectral, SAR images, LiDAR point clouds, elevation models, street-view images, meteorological, socio-economic data, etc.)
• integrate multiple data sources, including sensor data and geographic information layers (big GeoData)
• engage with application domain experts to co-design effective solutions (e.g., experts in urban management and planning, agriculture and food security, land administration, glaciology)
• engage with user groups and stakeholders from the private, public and institutional sectors to tackle real societal problems and validate the effectiveness of the proposed solutions
• engage with the scientific community and working groups to be an active member in shaping the research mission of the community
• embrace open science principles whenever possible to make research outcomes freely and easily accessible to the community
• foster the development of interpretable and trustworthy AI solutions to support decision making and policy definition

Over the past years, I have investigated the use of deep learning in Earth observation, researching on i) methodological aspects of the design and training of deep learning models, as well as ii) applied aspects concerning the use of such models to address real-world geospatial applications. If you want to learn more about my research, please see my publications.