... pour la spécialité "Terre solide"


Automatic monitoring of landslides from satellite optical images

5 mois, février-juin 2022

Niveau de formation et prérequis : M1 in Geosciences or Remote Sensing or Computing sciences. Interest for landslide monitoring. Good knowledges of statistical data processing (Matlab or Python). Knowledges of GIS can also be valued.
Laboratoire et encadrant : ISTerre Grenoble, Pascal Lacroix
Mots clés : landslides, optical images, monitoring, image correlation

Lire la suite

Deep learning application to earthquake detection and characterisation

Deep learning application to earthquake detection and characterisation

Deep learning application to earthquake detection and characterisation

The internship will be based in ISTerre, University of Grenoble under the supervision of Josipa Majstorović (skilful in CNNs and earthquake detection), Piero Poli (skilful in earthquake detection and seismology in general, piero.poli univ-grenoble-alpes.fr) and Sophie Giffard-Roisin (skilful in AI using remote sensing for natural hazards).

Lire la suite

Surface displacements in the 1980 Mw6.9 Irpinia earthquake (Italy) ; new constraints from optical image correlation

On 23rd November 1980, the Mw 6.9 Irpinia earthquake devastated the Campania region of southern Italy, killing 2.5k people, injuring 8k, and leaving 250k homeless. The earthquake represents one of the worst natural disasters to have affected Italy in modern history. In this project, the student will take advantage of new image processing methods to build a high resolution mosaic of aerial photos acquired before and after the earthquake, from which ground displacements close to the surface (...)

Lire la suite

Development of satellite image registration/correlation techniques using Deep Learning

Title : Development of satellite image registration/correlation techniques using Deep Learning
Keywords : image processing, machine learning, registration, earth science, seismic faults, remote sensing
Advisors : James Hollingsworth (ISTerre) Sophie Giffard-Roisin (ISTerre) Mauro Dalla Mura (GIPSA-Lab)
Summary : Recent developments in optical geodesy, in which co-registered satellite/aerial images spanning a period of time can be cross- correlated (with sub-pixel precision) to retrieve (...)

Lire la suite