Latest Tweets

Can we achieve through Earth Observation and Machine Learning a global and systematic observation of world’s forests and accurately measure deforestation?

Francescopaolo Sica


Francescopaolo Sica received the Laurea (M.S.) degree (summa cum laude) in telecommunication engineering and the Ph.D. degree in information engineering from the University of Naples Federico II, Naples, Italy, in 2012 and 2016 respectively. He is currently a Researcher at the Microwaves and Radar Institute, German Aerospace Center (DLR), Oberpfaffenhofen, Germany.

Since January 2019 he is pursuing the Living Planet Fellowship post-doctoral program of the European Space Agency with the project HI-FIVE (High-Resolution Forest Coverage with InSAR & Deforestation Surveillance). Within this project, he is investigating how to achieve a global and systematic observation of the world’s forests and measure deforestation through Earth Observation and Machine Learning algorithms.

From November 2014 until February 2016, he has been visiting the DLR Remote Sensing Technology Institute (EOC), working as a guest Ph.D. student on statistical methods for the estimation of interferometric parameters. Previously, since 2012, he has been with the Italian National Research Council (IREA-CNR) of Naples, where he started working on multi-temporal/multi-baseline SAR interferometry applications for deformation monitoring.

His research interests include the processing of synthetic aperture radar (SAR) images for single and multi-baseline interferometry with specific application to surface deformation monitoring, digital elevation model (DEM) generation, and land cover classification. Recent interests concern the development of deep learning algorithms for statistical inference and land cover classification from SAR, optical, and multi-spectral data. Dr. Sica was the recipient of the IEEE Student Prize 2012 for the best master thesis.


Research objectives

  • Development of novel and efficient algorithms for forest mapping with Sentinel-1 data stacks
  • Exploration of the potential of repeat-pass interferometry with Sentinel-1 for classification purposes
  • Quantification of on-going deforestation and generation of large-scale maps of changes and deforestation rate
  • Optimisation of the approach for the detection of changes in terms of resolution in space (high-resolution maps) and time (quick response to deforestation activities).

Read more in the research project sheet.

Scientific papers

Conference papers
  • Pulella, A., Sica, F., & Rizzoli, P. (2018). Monitoring deforestation in the Amazon basin using Sentinel-1 interferometric SAR time series. Kleiheubacher Tagung 2018
  • Rizzoli, P., Bello, J. L. B., Pulella, A., Sica, F., & Zink, M. (2018, July). A Novel Approach to Monitor Deforestation in the Amazon Rainforest by Means of Sentinel-1 and Tandem-X Data. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 192-195). IEEE.
  • Sica, F., Pulella, A., & Rizzoli, P. (2019, July). Forest Classification and Deforestation Mapping by Means of Sentinel-1 InSAR Stacks. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 2635-2638). IEEE.
  • Bueso Bello, J. L., Rizzoli, P., & Sica, F. (2019). Estimating the Deforestation Rate in the Amazon Rainforest from Sentinel-1 and TanDEM-X Multi-Temporal Stacks. In Proceedings of the ESA Living Planet Symposium. ESA.


email address