Skip to main content

Volcano-seismic Unsupervised Labelling and ClAssificatioN Embedded in A Real-time Scenario

Periodic Reporting for period 1 - VULCAN.ears (Volcano-seismic Unsupervised Labelling and ClAssificatioN Embedded in A Real-time Scenario)

Reporting period: 2017-11-01 to 2019-10-31

Active volcanoes have a big impact on the global economy and society. Current Volcano Monitoring (VM) is mainly based on the evaluation on the seismic activity, the main input used for eruption forecasting and early warning systems. The usual way to track this activity is to detect relevant events in a continuous data stream and to classify those events into groups or classes according to their physical origin, paying special attention to those classes acting as eruption precursors or involving population safety. In most Volcano Observatories (VOs) this Volcano-Seismic Recognition (VSR) is manually carried out by expert technicians, but, during a crisis, the VSR cannot be performed neither fast enough nor in a reliable way in order to quickly evaluate possible hazards.

Even if is estimated that exist around 800 active volcanoes in the world, very few observatories have their own VSR system. Most VOs
demand an automatic VSR solution to monitor the seismic precursors and classes which compromise casualties as lahars or phyroclastic flows.
However, to deploy a customised VSR system takes time, requires qualified operators and labelled databases (DBs), which is not easily affordable.
Even more, the built system won't be exportable to other volcanoes, and can become inefficient if the seismic activity patterns change.

The ultimate goal of the VULCAN.ears proposal is to provide an automatic, universal, Volcano-Independent Seismic Recognition (VI.VSR) system, easily integrable into any VO to allow online hazard assessment by real-time analysis of the seismicity. To fulfill this aim, two main objectives have to be achieved:

(i) To design robust, VI.VSR recognition models, by gathering lots of events from different volcanoes, efficiently describing each event class.

(ii) To maximise the system applicability: disseminating it and integrating it into several VOs and eruption forecasting (EF)
frameworks to obtain useful feedback from partners, encompassing the system improvement and usability.

At the end of the -administrative- lifetime of VULCAN.ears project, evaluating VI.VSR technologies in real-case scenarios, we
can draw these conclusions:

1. Volcano-Independent VSR is actually a breakthrough technology aimed to become the next step of seismic
monitoring. The results achieved so far prove that our VI.VSR system is able to operate in real-time, recognising events of
a given volcano using universal VSR models, built by universal DBs obtained in other volcanoes.

2. Modern VOs have a real need and interest in installing VI.VSR systems. Built from a scratch their own systems
requires an effort that not all the VOs can afford. Therefore, the dissemination of a universal VI.VSR
framework easy to be embedded in the VOs is a must in order to find a solution. The Open Access software distributed by
VULCAN.ears solves this ‘must’.

3. The improvement of the VI.VSR system incorporating new universal VSR models depends on the international
collaboration and transfer of knowledge among partners. This is an ongoing task, beyond the duration of this
project, with a direct social impact, specially in developing countries with active volcanoes but few resources.
The tasks performed to achieve the VULCAN.ears objectives have been grouped into work packages [WP.s] satisfactory completed at the end of the project. They can be listed as:

[WP.0]: Search of robust procedures to describe the volcano-seismic events
[WP.1]: Improvement of existing state-of-the-art VSR algorithms and implementation of new ones
[WP.2]: Deployment of an early-stage VI.VSR system, to be shared among partners
[WP.3]: Design of a Graphical User Interface (GUI) to increase the usability of the VI.VSR framework
[WP.4]: VSR integration into monitoring frameworks of volcano-observatories (VOs)
[WP.5]: Scientific feedback from VOs to improve the VI.VSR system gathering data and building universal models
[WP.6]: VSR system integration with Eruption Forecasting (EF) systems
[WP.7]: VULCAN.ears result & product dissemination

The completion of these work packages produce relevant results synthesized in:

- The universal DB, with labelled events collected in more than 21 volcanoes all over the world
- The implementation of a portable VI.VSR monitoring system, which includes VSR models of 10 volcanoes, 6 modelsets of
combined-volcanoes and 2 universal VSR modelsets
- The dissemination of a free-software framework for boosting the usability system compose of:
> pyVERSO: for building own VSR models
> geoStudio: to graphically use the VI.VSR models
> liveVSR: for performing online real-time, continuous, VSR monitoring

The actions taken to disseminate and exploit the results include:

- publishing international, peer-reviewed, scientific journals and
more than 15 communications to international geophysic conferences and workshops
- (co)organizing 3 workshops and seminars to introduce the VSR-related technologies
- Partnering with 12 countries & 18 institutions, collaborating with 4 international projects and creating 1
international WorkGroup (ALUE_VSR) for the VI.VSR development
- Promoting events to reach a wider society, as 3 public talks and announcing VULCAN.ears
in 7 public (digital & press) media and social networks
The main innovation outputs achieved by VULCAN.ears can be plotted as:

- Seismic waveform standardisation to denoise the signal and facilitate its description, increasing the modelling efficiency.
- A parallel architecture composed of dedicated VSR channels, focused to recognise events of a given class,
discriminating other types
- The proposal of alternative models to be used in noisy VSR scenarios
- The final implementation of the proposed universal and portable VI.VSR system, able to operate in real-time

The accomplishment of the scheduled tasks alongside the exploitation of the results has a direct impact in different actors:

a) For the general society: the main VI.VSR goal is to preserve the safety of population living close to a volcano.
VULCAN.ears improves the risk assessment providing real-time monitoring, beside useful analysis for
eruption forecasting, which can reduce the economical loss in case of a positive forecasting.

b) Potential users of the VI.VSR technology: the freely disseminated software can be interesting for
any observatory and institution related to real-time monitoring and eruption forecasting (as EPOS, USGS, WOVOdat,
IRIS),... Also research institutions can import the innovative VULCAN.ears technologies, easily exportable to other scientific areas.

c) Impact on policy and administrations: environmental EU policy can foster VI.VSR tools in European
observatories and boost the cooperation with developing countries (including but not limited to
Latin-American countries) where population risk due to active volcanism is a reality.

Due to the already started collaboration with partner institutions in other projects,
there are lots of opportunities to continue improving and disseminating the VI.VSR area. New outcomes and the installation
of VI.VSR software in European and Antarctic volcanoes are scheduled in the next months.
Once the VI.VSR framework will be well-established, its adoption in other institutions will be encouraged.
Scheme of a Volcano-Independent Seismic Recognition (VI.VSR) system