MOUNTS | Monitoring Unrest From Space


- system description and recent eruptive events:

Valade, S., Ley, A., Massimetti, F., D’Hondt, O., Laiolo, M., Coppola, D., Loibl, D., Hellwich, O., Walter, T.R., Towards Global Volcano Monitoring Using Multisensor Sentinel Missions and Artificial Intelligence: The MOUNTS Monitoring System, Remote Sens., 2019, 11, 1528

BibTeX reference

- algorithm used to analyze Sentinel-2 images:

Massimetti, F., Coppola, D., Laiolo, M., Valade, S., Cigolini, C., Ripepe M., Volcanic Hot-Spot Detection Using SENTINEL-2: A Comparison with MODIS–MIROVA Thermal Data Series, Remote Sens., 2020, 12(5), 820

- algorithm used to filter speckle from Sentinel-1 images:

Davis, T., Jain, V., Ley, A., D’Hondt, O., Valade, S., Hellwich, O., Reference-free despeckling of Synthetic-Aperture Radar images using a deep convolutional network, IGARSS 2020 (ACCEPTED)

About the project

MOUNTS is a project initiated in April 2017, whose aim is to develop an operational monitoring system for volcanoes worldwide using satellite imagery. It currently focuses on processing of Sentinel-1 (SAR), Sentinel-2 (SWIR), and Sentinel-5P (TROPOMI) data. Artificial intelligence "plugins" are developed and implemented in the processing chain to assist monitoring tasks.

The project is lead by Sébastien Valade, and was from April 2017 to October 2019, funded by GEO.X and carried at TU-Berlin (Computer Vision & Remote Sensing group, Prof. O. Hellwich) and GFZ (Physics of Earthquakes and Volcanoes section, Priv. Doz. T. Walter). Since March 2020, the project is carried at UNAM (Instituto de Geofísica, Mexico City). The server running both the system and website is however still hosted at CV TU-Berlin, with the kind agreement of Prof. Hellwich.

MOUNTS is strongly inspired by the operating MIROVA system, with which tight collaborations are ongoing.

Credits & Acknowledgements

- TU-Berlin:

. Andreas Ley developed and trained the convolutional neural network used by MOUNTS to detect ground deformation from Sentinel-1 interferograms (github).

. Olivier D'Hondt developed the NDSAR toolkit for SAR speckle filtering used in Valade et al. (2019).

. Timothy Davis & Vinit Jain, under the supervision of Andreas Ley, developed and trained the convolutional neural network used by MOUNTS to despeckle Sentinel-1 SAR amplitude images. Submitted paper to IGARSS conference 2020 (Davis, Jain et al.): "Reference-free despeckling of Synthetic-Aperture Radar images using a deep convolutional network."

- MIROVA: members of MIROVA developed the algorithm used to detect hot pixels within the Sentinel-2 SWIR bands (Massimetti et al., 2020). MIROVA is a collaborative project between the Universities of Turin and Florence (Italy). Developments are underway to increase the interactivity between MOUNTS and MIROVA.

- Sentinel data are freely available through ESA's Copernicus Open Access Hub, and are partially processed with the free SNAP toolboxes. Earthquake catalogs are provided by GEOFON (GFZ Potsdam) and USGS, and interrogated using the Pyrocko Toolbox.

Use of the data

The products available on the website are value-added products created from freely available Sentinel data provided by ESA. The products are released under the following conditions: permission to freely copy, share and quote for non-commercial purposes, with attribution to MOUNTS and ESA as the original source. If used for academic purposes, contacting Sébastien Valade ( and citing the above mentioned publication (Valade et al. 2019 Remote Sensing) is kindly appreciated.


The information presented within the MOUNTS website are provided "as is" and users bear all responsibility and liability for their use of data and images, and for any indirect, incidental or consequential damages arising out of any use of, or inability to use, the data.