Conférence GM & ED Gaïa

An introduction to Deep Learning for Remote Sensing Earth Observations analysis with applications on land cover mapping

By Dino IENCO (INRAE, INRIA, Montpellier)

à 14h amphi 23.01

campus Triolet, Université de Montpellier

Participer à la conférence en ligne (ID de réunion : 939 6070 1102)

The talk will cover a gentle introduction to deep learning approach for the analysis of remote sensing data. Firstly, I will present the current landscape in terms of remote sensing data, then I will discuss the difference between standard machine learning methodologies and deep learning methods. After that, a panorama of the main concepts behind neural network will be provided. Finally, more of the time will be dedicated to provide examples of applications of deep learning approaches in the context of remote sensing data analysis with applications spanning from satellite image time series analysis for land cover characterization to multi-source remote sensing data exploitation for glacial moraine mapping.

Dino IENCO received the M.Sc. and Ph.D. degrees in computer science both from the University of Torino, Torino, Italy, in 2006 and 2010, respectively. He joined the TETIS Laboratory, IRSTEA, Montpellier, France, in 2011 as a Junior Researcher. His main research interests include machine learning, data science, graph databases, social media analysis, information retrieval and spatio-temporal data analysis with a particular emphasis on remote sensing data and Earth Observation data fusion. Dr. Ienco served in the program committee of many international conferences on data mining, machine learning, and database including IEEE ICDM, ECML PKDD, ACML, IJCAI as well as served as a Reviewer for many international journal in the general field of data science and remote sensing.