[Humans of FDL] Ramona Pelich
Meet EO Researcher Ramona Pelich
Ramona talks about the future of EO + AI and a french guy that will sleep at your house.
FDL: Hi Ramona. We are asking each of the researchers about their background. Can you tell us a little about your journey leading you to the Disaster Detection Challenge at FDL Europe?
RP: I’d be happy to. I am originally from Romania where I started my engineering studies in telecommunications. At the end of my masters in France, I did an internship related to earth observation which sparked my interest in this field. I continued with a PhD in Earth Observation at Telecom Bretagne and Collecte Localisation Satellites (CLS), working with radar images for maritime surveillance. After my PhD, I started a postdoc at the Luxembourg Institute of Technology where I’m still working with radar images, but now focused also on monitoring floods.
FDL: What are some of the things that excite you most in your field?
RP: I believe there is great potential around flood predictions. Radar is great for getting flood data immediately after an event, but to predict a flood, you need something more. One of the great things we have now is satellite imagery going back years and years, where we can look at what happened in past and start to predict what areas are prone to floods. Yet having the historical satellite imagery alone isn’t enough. And this is where AI is going to play an increased role.
One of the great things about the FDL Europe experience has been getting to interact with AI specialists from computer vision. Humans are limited in seeing complex patterns emerge from tons and tons of satellite images. Moreover, even when the same place is imaged with a high frequency over a period of many years like for the ESA satellite missions, the associated petabytes of data hinder the human analysis of patterns. However, computer vision offers us a tremendous new tool to be able to understand changes over time and begin running predictions for the future. The biggest problem - AI people and remote sensing people don’t speak the exactly same language. We’ve only started to scratch the surface in this area, but I now have a much better understanding of what is possible, and what is needed to overcome those barriers.
FDL: Do you have any favorite quotes, books, movies, TV shows?
RP: Well I do have a favorite quote. In fact, I included it in my Phd thesis. Grace Murray Hopper said “A ship in port is safe, but that is not what ships are built for. Sail out to sea and do new things”.
And as far as entertainment, I like to watch a tv series about a guy from France travelling around the world. Each episode is about one country, he is travelling alone and films himself and the people he is meeting. The purpose is not to visit the very touristic places but to interact with the people living there, so he tries to visit their homes… and learn many things about their culture and ways of living. The show is called “J’irais Dormir Chez Vous” [I’ll Sleep At Your House].
About Dr. Ramona Pelich
Dr. Ramona Pelich received a B.S. degree and an M.S. degree in signal and image processing from both the “Traian Vuia” Polytechnic Institute of Timisoara, Romania and the Institut Mines Télécom, Télécom Bretagne, France, in 2010 and 2012, respectively. She received her Ph.D. degree in remote sensing and image processing from the Institut Mines Télécom, Télécom Bretagne in 2015. Between 2012 and 2015, she was with Collecte Localisation Satellites, France and the Institut Mines Telecom, Télécom Bretagne, working on ship detection and characterization from Synthetic Aperture Radar (SAR) imagery linked with cooperative vessel tracking data. In 2016 she joined the Environmental Research and Innovation (ERIN) Department, Luxembourg Institute of Science and Technology, Luxembourg. Her research interests include signal and image processing techniques applied to remote sensing data. The developed scientific algorithms are applied in different fields such as large-scale flood hazard mapping, vessel detection, urban mapping, etc.