- Chercheur postdoctoral en IA appliquée au système électrique, Mines Paris - PSL
Je suis chercheur postdoctoral à Mines Paris – PSL, où je travaille sur la fiabilité et la transparence des algorithmes de deep learning déployés dans l’industrie. Mes recherches se situent à l’intersection de l’IA explicable, de la vision par ordinateur et de la télédétection, avec un focus particulier sur la cartographie des installations photovoltaïques sur toiture.
Experience
-
–presentChercheur postdoctoral en IA appliquée au système électrique, Mines Paris - PSL
Education
-
2024Université PSL (Mines Paris), Doctorat
Publications
-
2025One Wave to Explain Them All: A Unifying Perspective on Feature Attribution, ICML
-
2024Enhancing the Reliability of Deep Learning Models to Improve the Observability of French Rooftop Photovoltaic Installations, Thèse de doctorat
-
2024Remote-Sensing-Based Estimation of Rooftop Photovoltaic Power Production Using Physical Conversion Models and Weather Data, Energies
-
2023A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata, Scientific Data
-
2023Can We Reliably Improve the Robustness to Image Acquisition of Remote Sensing of PV Systems?, TCCML @NeurIPS
-
2023Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain, XAI-in-Action @NeurIPS
-
2022Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping, MACLEAN @ECML-PKDD
Contact Gabriel for
- General
- Media request
- Speaking request
- Consulting / Advising
- Research collaboration
- Research supervision
- Website
- Article Feed
- ORCID
- Joined
