Carmelo has a background in forestry science, with a specialization in forest resources monitoring and management through geospatial data science applications and time series analysis. He has experience with all kind of GIS softwares and enjoys working in R and Python programming languages. Carmelo's current research is focused on using statistical and machine learning methods to model tree species dynamics.

Carmelo is an external PhD, working as a research assistant at the OpenGeoHub Foundation. He works with designing and conducting research from experimental designs to scientific visualization and communication of science, importing and processing spatial and spatiotemporal data, assisting in training courses and helping in the production of educational materials.

Specific tasks include but are not limited to:

• Installing and maintaining software on local, server and cloud platforms,
• Developing and testing new algorithms and approaches to predictive mapping and machine learning,
• Optimizing computing/minimizing production costs,
• Creating complete data sets, packaged software and software manuals, including tutorials for other researchers,
• Contributing to Open Source Software and Open Data communities through FOSS4G, R, Python and similar communities.

2022 - ongoing

Open-Earth-Monitor, a cyberinfrastructure to accelerate uptake of environmental information
and help build user communities at European and global levels.

The Open-Earth-Monitor consortium consists of 23 partner organizations from and outside Europe. The main goals are to: 

• Produce an inventory of user needs, data and knowledge that will be used to develop a general framework for increasing uptake and accessibility/exploitability of environmental observation information;
• Achieve notable and permanent improvement in access for European stakeholders to existing European and global environmental observation data and actionable information by reducing data complexity and increasing accessibility;
• A suite of intuitive tools to enable targeted end-users to monitor the status of natural resources at European and global scales, and production of environmental Business-2-Business solutions;
• A comprehensive and systematic platform to enhance the FAIRness (Findability, Accessibility, Interoperability and Reusability) of environmental data by upholding and implementing the values of the European AI act and European GDPR Act; 
• An operational solution for processing and serving Earth Observation data, in-situ environmental data, and Artificial Intelligence, Machine Learning and HPC models (OEMC-computing-engine).

One of the most innovative aspects of this project is that people are placed at the centre of the design and implementation of the cyberinfrastructure: a dedicated Work Package will collect and analyze an inventory of user requests and needs, as well as data and ground knowledge to develop a general framework for increasing uptake and accessibility/exploitability of environmental observation information. Stakeholders will be engaged in the early stage of the design, since the very start the project, through workshops and early user-testing.

2020 - 2022

Geo-harmonizer: EU-wide automated mapping system for harmonization of Open Data based on FOSS4G and Machine Learning

The GeoHarmonizer project aims at reducing problems of national data with using seamless complex (geographical) data over the entire extent of the EU, and “opening data” through:

• using Open Data licenses, 
• enabling wider public access to the data by not only scientists and specialists, but also non-professionals, 
• facilitating increased use of EC-funded data without imposing any expectations on users to possess specialised or costly infrastructure, 
• working closely with the national authorities, organizations and NGOs including the existing EC-funded systems such as DIAS, Copernicus programme and similar. 

We use the Geo-harmonizer tools and data to generate decision-ready layers such air quality and pollution, potential natural vegetation, potential for producing energy from solar insolation, wind energy and similar. To calculate these value-added decision-ready maps, we use topographic data (DEMs), Earth observation (EO) data, hydrological and meteorological data that we map using automated mapping systems largely based on Machine Learning algorithms available in the Open Source software.