Periodic Reporting for period 1 - VOLCANOWAVES (State of unrest of active VOLCANOes through advanced seismic WAVES analysis - An application to eruption forecast modelling.)
Période du rapport: 2018-09-01 au 2020-08-31
The overarching goal of this project was to advance the current understanding of the relation between seismicity and eruption at volcanoes. The application of advanced signal processing and machine learning techniques allows characterizing volcanic unrest and to better identify precursors to eruptions. New algorithms for automatic earthquake classification were developed and applied to seismic signals recorded at active volcanoes. New catalogues of volcanic earthquakes were generated with unprecedented resolution, which deliver valuable information for the future design of Early Warning systems.
The project’s main research objectives (Ob), reached during the lifetime of the project, were:
Ob.1. To build a database of continuous and segmented seismic data from the volcanoes than were representative of different eruptive scenarios. The database was built with modern standards, usingdata and metadata formats, event labelling and other protocols that are widely adopted in the volcanological and geophysical communities.
Ob.2. To develop new metrics and methods for the characterization of volcano-seismic signals via development and application of advanced signal processing algorithms.
Ob.3. To develop automated methods for the identification of temporal changes in seismic time series that could be used to produce forecasts of impending volcanic activity.
The project’s main research objectives (Ob), reached during the lifetime of the project, were:
Ob.1. To build a database of continuous and segmented seismic data from the volcanoes than were representative of different eruptive scenarios. The database was built with modern standards, usingdata and metadata formats, event labelling and other protocols that are widely adopted in the volcanological and geophysical communities.
Ob.2. To develop new metrics and methods for the characterization of volcano-seismic signals via development and application of advanced signal processing algorithms.
Ob.3. To develop automated methods for the identification of temporal changes in seismic time series that could be used to produce forecasts of impending volcanic activity.
Ob. 1
A new seismic database was constructed with data from selected volcanoes the represent different unrest and eruption scenarios. This allowed the organization of data and metadata in standardised formats. These data formed the basis for Ob.2 and Ob.3 of the project. They were used to produce catalogues of earthquakes with classification labels by applying Machine Learning methods. Seismic data were transformed to standard formats using open-source software. The size and variety of data formats represented a challenge. Results: In order to manage such a large set of data and metadata, in collaboration with the host institution group, I participated to design a mySQL relational database to archive and efficiently access seismic data and the related metadata. I contributed in writing a scientific paper focussed on the implementation and management of this database. Currently, this manuscript is under UGR internal review prior to submission to Computers & Geosciences, an ELSEVIER, an international peer reviewed journal.
Ob. 2:
I manually classified seismic signals for each case study volcano to increment the initial master DB of labelled events (that is, a catalogue of labelled signals extracted from continuous seismic data streams) created in Ob1. Events were separated on the basis of both their time and frequency domain characteristics to obtain a large dataset of more 10000 reliably classified seismic events. To achieve this objective, I overseen the implementation of the new Python Interface for the Classification of Seismic Signals (PICOSS). The following step was to create, with the support of the host research team, a new algorithm for supervised classification that allowed clustering of catalogued events in different families. This algorithm was based on the quantification of metrics linked to changes in amplitude and frequency within each event. Results: (i) I obtained a new labelled dataset and the corresponding parameters (ime and frequency domain) catalogues; (ii) I designed, in collaboration with the host research group a modular open source software, called PICOSS (doi:https://doi.org/10.1016/j.cageo.2020.104531) with a graphical user interface designed for detection, segmentation and classification, focusing on exportability and standardization of data formats. The users can select automatic or manual workflows to select and label seismic data from a comprehensive suite of tools, including deep neural networks; (iii) In addition, I have participated to build a new platform (VINEDA-doi: 10.3389/feart.2019.00335) for automatic identification of acoustic volcanic signals. I joined an international team (a joint collaboration between Italy, UK and Spain) focussing the analysis of infrasound signals in volcanic environments. Volcano infrasound used jointly with seismic data can provide valuable information on magma and eruption at active volcanoes.
Ob. 3:
Finally, I compared the automatically labelled seismic signals with the ones classified manually in order to benchmark the new classification algorithms via unsupervised ML procedures. This part of the project focused on the recognition of patterns and regularities in data. I established which set of features and architectures were most appropriate for signal characterization and to identify changes in seismic timeseries as potential precursor of every eruptive process. To reach this objective, I have used Deep Learning architectures implemented in the popular TensorFlow Python libraries. Results: (i) I analysed more than 55000 earthquakes using advanced ML algorithms in order to perform an automatic analysis aimed at characterizing the temporal evolution of clusters of similar events, that are well correlated with the occurrence of eruptive activity, suggesting that they could be a common precursor to eruptive events; (ii) I contributed to design, in collaboration with the host research group, a new method to detect subtle changes in continuous seismic data potentially associated with the evolution of unrest and impending eruptions, for which specialised architectures are required. We implemented a new framework to monitor changes in continuous seismic time series based on Bayesian Deep Learning theory. I participated to writing a scientific paper focussed on the implementation and management of this ML architecture, showing the results obtained. Currently, this manuscript is under review in IEEE-TGRS, an international peer reviewed journal.
In addition, other 12 scientific reports are open access on EGU, AGU and INGV conference repositories.
A new seismic database was constructed with data from selected volcanoes the represent different unrest and eruption scenarios. This allowed the organization of data and metadata in standardised formats. These data formed the basis for Ob.2 and Ob.3 of the project. They were used to produce catalogues of earthquakes with classification labels by applying Machine Learning methods. Seismic data were transformed to standard formats using open-source software. The size and variety of data formats represented a challenge. Results: In order to manage such a large set of data and metadata, in collaboration with the host institution group, I participated to design a mySQL relational database to archive and efficiently access seismic data and the related metadata. I contributed in writing a scientific paper focussed on the implementation and management of this database. Currently, this manuscript is under UGR internal review prior to submission to Computers & Geosciences, an ELSEVIER, an international peer reviewed journal.
Ob. 2:
I manually classified seismic signals for each case study volcano to increment the initial master DB of labelled events (that is, a catalogue of labelled signals extracted from continuous seismic data streams) created in Ob1. Events were separated on the basis of both their time and frequency domain characteristics to obtain a large dataset of more 10000 reliably classified seismic events. To achieve this objective, I overseen the implementation of the new Python Interface for the Classification of Seismic Signals (PICOSS). The following step was to create, with the support of the host research team, a new algorithm for supervised classification that allowed clustering of catalogued events in different families. This algorithm was based on the quantification of metrics linked to changes in amplitude and frequency within each event. Results: (i) I obtained a new labelled dataset and the corresponding parameters (ime and frequency domain) catalogues; (ii) I designed, in collaboration with the host research group a modular open source software, called PICOSS (doi:https://doi.org/10.1016/j.cageo.2020.104531) with a graphical user interface designed for detection, segmentation and classification, focusing on exportability and standardization of data formats. The users can select automatic or manual workflows to select and label seismic data from a comprehensive suite of tools, including deep neural networks; (iii) In addition, I have participated to build a new platform (VINEDA-doi: 10.3389/feart.2019.00335) for automatic identification of acoustic volcanic signals. I joined an international team (a joint collaboration between Italy, UK and Spain) focussing the analysis of infrasound signals in volcanic environments. Volcano infrasound used jointly with seismic data can provide valuable information on magma and eruption at active volcanoes.
Ob. 3:
Finally, I compared the automatically labelled seismic signals with the ones classified manually in order to benchmark the new classification algorithms via unsupervised ML procedures. This part of the project focused on the recognition of patterns and regularities in data. I established which set of features and architectures were most appropriate for signal characterization and to identify changes in seismic timeseries as potential precursor of every eruptive process. To reach this objective, I have used Deep Learning architectures implemented in the popular TensorFlow Python libraries. Results: (i) I analysed more than 55000 earthquakes using advanced ML algorithms in order to perform an automatic analysis aimed at characterizing the temporal evolution of clusters of similar events, that are well correlated with the occurrence of eruptive activity, suggesting that they could be a common precursor to eruptive events; (ii) I contributed to design, in collaboration with the host research group, a new method to detect subtle changes in continuous seismic data potentially associated with the evolution of unrest and impending eruptions, for which specialised architectures are required. We implemented a new framework to monitor changes in continuous seismic time series based on Bayesian Deep Learning theory. I participated to writing a scientific paper focussed on the implementation and management of this ML architecture, showing the results obtained. Currently, this manuscript is under review in IEEE-TGRS, an international peer reviewed journal.
In addition, other 12 scientific reports are open access on EGU, AGU and INGV conference repositories.
Ob. 1
This new relational mySQL database will contribute to the field of volcano seismology, owing to its versatility in storing processed information resulting from the application of signal processing techniques for earthquake classification.
Ob. 2:
The proposed approach will open new avenues towards the use of these algorithms to detect and classify seismic signals that are relevant to monitor volcanoes and to forecast their activity. A valuable aspect of this workflow is that it allows to perform fast and efficient analyses of big seismic data. The main innovation of the software created in this project is to support both supervised and unsupervised detection, data labelling and classification tasks. PICOSS includes functionalities that can be easily adapted for the operational requirements of volcano observatories. The scientific and technological quality of this interface relies on the ease of access to a variety of signal processing techniques routinely used at volcano observatories.
Ob. 3:
The methods developed are transferrable to other volcanoes and seismically active regions, thus opening new possibilities for volcano-seismic research monitoring. This new approach will be of wide interest within the international geophysical and volcanological community as it provides flexible tools that allow rapid investigation of large sequences of volcano seismic records, thus contributing to improve our ability to detect and track volcanic unrest and to forecast volcanic eruptions
This new relational mySQL database will contribute to the field of volcano seismology, owing to its versatility in storing processed information resulting from the application of signal processing techniques for earthquake classification.
Ob. 2:
The proposed approach will open new avenues towards the use of these algorithms to detect and classify seismic signals that are relevant to monitor volcanoes and to forecast their activity. A valuable aspect of this workflow is that it allows to perform fast and efficient analyses of big seismic data. The main innovation of the software created in this project is to support both supervised and unsupervised detection, data labelling and classification tasks. PICOSS includes functionalities that can be easily adapted for the operational requirements of volcano observatories. The scientific and technological quality of this interface relies on the ease of access to a variety of signal processing techniques routinely used at volcano observatories.
Ob. 3:
The methods developed are transferrable to other volcanoes and seismically active regions, thus opening new possibilities for volcano-seismic research monitoring. This new approach will be of wide interest within the international geophysical and volcanological community as it provides flexible tools that allow rapid investigation of large sequences of volcano seismic records, thus contributing to improve our ability to detect and track volcanic unrest and to forecast volcanic eruptions