Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2
<script src=
Published in ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science vol 12667, 2020
We set up a comparison ef existing methods for poverty estimation, and compare them in Malawi.
Recommended citation: Robin Jarry, Marc Chaumont, Laure Berti-Équille, Gérard Subsol. Assessment of CNN-based methods for poverty estimation from satellite images. In Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10-15, 2021, Proceedings, Part VII (p. 550-565). Springer International Publishing. Link.
Published in IGARSS, 2023
We studied if a deep learning model could benefit from spatio-temporal data to predict the evolution of Nighttime Light, a classic socio-economic proxy.
Recommended citation: Robin Jarry, Marc Chaumont, Laure Berti-Équille, Gérard Subsol. Comparing Spatial and Spatio-Temporal Paradigms to Estimate The Evolution of Socio-Economical Indicators from Satellite Images. In IGARSS 2023 - IEEE International Geoscience and Remote Sensing Symposium (p. 5790-5793). IEEE. Link.
Published:
A ready to use short demonstration of several possibilities with Geemap. The objective is to show that, with minimum effort, it’s possible to create a model that estimates the population count for a given lat/lon and create an interactive map to visualize the results.
Published:
How to estimate evolution patterns from satellite image time series ? There are plenty of solution in the scientific literature, while few of them focus on decades-long evolutions of real value indicators.
6-9th Grade Classes, Collège Pierre-Mendès France, 2018
I taught mathematics to middle school students, for two half-days per week during one year.
2nd year students, University of Nîmes, 2020
My first teaching experiment at the university. The lecture was Graph Algorithms. 50h.
Bachelor degree students, University of Montpellier, 2023
Teaching position in computer science. Amount of teaching: 192h (tutorial classes)