Abstract
In the last 9 years, the amount and the quality of geophysical and volcanological observations of Stromboli's' activity have undergone a marked increase. This new information highlighted that the landslides on the Sciara del Fuoco flank are tightly linked to the volcanic activity. Actually, at the beginning of the December 28, 2002, effusive eruption, the seismic monitoring network was less dense than now, and therefore it is not known if there was an increase in the landslide rate before the eruption. Despite this, it is known that a big landslide occurred 2 days after the beginning of the eruption which caused a tsunami (December 30, 2002). More recently, the effusive eruption in February 2007 was preceded by an increase in landslides on the Sciara del Fuoco flank, which were recorded by the seismological monitoring system that had been improved after the 2002–2003 crisis. These episodes led us to believe that monitoring the Sciara del Fuoco flank instability is an important topic, and that landslides might be significant short-term precursors of effusive eruptions at the Stromboli volcano. To automatically detect landslide signals, we have developed a specialized neural algorithm. This can distinguish between landslides and the other types of seismic signals usually recorded at the Stromboli volcano (i.e., explosion quakes and volcanic tremor). The discrimination results show an average performance of 98.67 %. According to the experience of the crisis of 2007, to identify changes that can be considered as precursors of effusive eruptions, we set up an automatic decision-making method based on the neural network responses. This method can operate on a continuous data stream. It calculates a landslide percentage index (LPI) that depends on the number of records that are classified by the net as landslides over a given time interval. We tested the method on February 27, 2007, including the beginning of the effusive phase. The index showed an increase as early as at 09:00 UTC on that day and reached its maximum value (100 %) at 12:00, about 40 min before the onset of the eruption. After the beginning of the effusive phase, the index remains high due to the blocks that roll down along the slope from the front of the lava flow. On the basis of these tests, we propose a decision-making method that is able to recognize a trend in the LPI similar to that of 2007 eruption, allowing the identification of precursors of effusive phases at the Stromboli volcano.
Similar content being viewed by others
Avoid common mistakes on your manuscript.
1 Introduction
The Stromboli volcano (Italy) is one of the most active volcanoes in the world, with moderate and persistent explosive activity. Its recent history is characterized by two effusive eruption episodes (Calvari et al., 2005; Martini et al., 2007) that were accompanied by dangerous phenomena, including a tsunami (La Rocca et al., 2004; Pino and Boschi, 2009; Tinti et al., 2005, 2006) on December 30, 2002, and paroxysmal explosions that occurred on April 5, 2003 (D’Auria et al., 2006), and on March 15, 2007 (Martini et al., 2007). These two effusive phases were associated with instability of the slope known as Sciara del Fuoco (Baldi et al., 2005; Falsaperla et al., 2006; Tibaldi, 2001). This structure is a weakness zone of the volcanic edifice that fractures when the explosive activity increases, giving rise to the effusive activity. In particular, during the 2002–2003 effusive phase, there was a partial collapse of this side that caused a tsunami, which spread to the nearby coast with waves up to 10 m high. After this episode, the northwest flank became unstable, and as many as 50 landslide signals were recorded per day (Martini et al., 2007).
The monitoring of the stability of Sciara del Fuoco is an important topic both from the scientific point of view and for Civil Protection purposes. In the framework of the real-time monitoring of the Stromboli volcano, different systems have been implemented to detect the instability of the Sciara del Fuoco. All these techniques rely on geodetic measurements. Their target is to detect an acceleration in the deformation rate of the volcano flank, in order to forecast its possible catastrophic failure. Puglisi et al. (2005) implemented an integrated geodetic monitoring system based on EDM and GPS measurements. Using a statistical analysis of EDM data, Nunnari et al. (2008) developed an early warning system to evaluate the level of hazard on Sciara del Fuoco.
Casagli et al. (2009) propose another geodetic monitoring system based on ground-based synthetic aperture radar (SAR) interferometry (GB-InSAR). This system is able to provide real-time images of the deformation rates on the Sciara del Fuoco flank and was shown to be an effective monitoring tool during the 2007 effusive eruption. However, the cited methods may be less sensitive to very local deformations, such as those that are associated with minor landslides that affect only the superficial part of the slope of the Sciara del Fuoco. In this case, the analysis of seismic signals recorded from the proximal stations can help significantly to identify signs of instability of the slope.
In January 2003, during the aforementioned effusive eruption, the Istituto Nazionale di Geofisica e Vulcanologia (INGV) installed a broadband seismic network to monitor the volcanic activity and to enhance the surveillance of the island (De Cesare et al., 2009). Due to these systems, changes in the very long period (VLP) seismicity of the island were later recorded, from about a month before the 2007 effusive eruption (Barberi et al., 2009; Giudicepietro et al., 2009; Martini et al., 2007). In addition, the new seismic monitoring system highlighted that the first seismic signal associated with a landslide occurred at around 09:00 UTC on February 27, 2007, and was followed by other similar signals. This behavior was recognized as an anomaly, and it was communicated to the Civil Protection authorities before the beginning of the effusive eruption. At 12:39 UTC on February 27, 2007, Stromboli volcano started an effusive phase (Barberi et al., 2009; Giudicepietro et al., 2009; Ripepe et al., 2009).
For this reason we believe that, together with geodetic monitoring, seismic signal analysis could also provide a valuable contribution to the monitoring of Sciara del Fuoco stability, with special reference to the opening of eruptive vents and in general with respect to an early warning of effusive eruptions.
Based on the seismological observations collected in the past 9 years, the present study proposes a system for the automatic detection of landslides that uses a multi-layer perceptron (MLP) neural network (Bishop, 1995). The output of this system is used here to implement a decision-making method that allows changes in the landslide rate to be highlighted. Several methods have been used for seismic event discrimination based on spectral analysis (Hartse et al., 1995; Gitterman et al., 1999) and cross-correlation technique (Joswig, 1990; Rowe et al., 2004). Also the neural networks have been successfully applied in the field of seismology for the detection and discrimination of different types of seismic signals (Cercone and Martin, 1994; Dowla et al., 1990; Dowla, 1995; Del Pezzo et al., 2003; Scarpetta et al., 2005; Tiira, 1999; Wang and Teng, 1995). In particular, for the Strombolian seismicity, it has already been demonstrated that it is possible to distinguish between landslides, explosion quakes and tremor signals using a three-class MLP network (Esposito et al., 2006). Furthermore, among the supervised methods different from the MLP network, the support vector machines (SVM) (Schffolkopf and Smola, 2002) have also often used for seismic patterns classification (Giacco et al., 2009; Masotti et al., 2006; Langer et al., 2009). A performance comparison between these two techniques showed that they tend to perform very similarly (Barabino et al., 1999; Osowski et al., 2004).
Since the aim of this study was the detection of landslides with respect to the other main seismic signals recorded by the monitoring network, the dataset examined was divided into two classes of signals: the first is called “landslide”, and it contains only the landslides; the second is called “other”, and it collects the other two typologies of events that mostly contribute to the seismic wavefield at Stromboli, namely, explosion quakes and volcanic tremor.
In the following, a brief introduction to the Stromboli monitoring network and the dataset is first presented, then in Sect. 3 the methods for the data parameterization are described. In Sect. 4 we explain how the landslide detection was realized by using a two-class MLP-based system. Section 5 describes the elaboration of the neural net output for the setting-up of a decision-making algorithm, and lastly, Sect. 6 is dedicated to our conclusions.
2 The Monitoring System of Stromboli and the Seismic Data
Currently, the Stromboli seismic network consists of 13 digital broadband stations (Fig. 1), equipped with Guralp CMG-40T sensors with frequency response of 0.02–60 s. It has a geometry that provides fine coverage over the island, except on the Sciara del Fuoco side, which represents a gap in the azimuthal distribution of the sensors because of its unapproachable terrain. However, there are some stations very close to the margin of this flank, such as STR8, STRA, STRB (see Fig. 1), that allow any signals that are generated from it, and in particular the landslides, to be well recorded. Thus, these stations are more sensitive to this type of signals which attenuates away from the Sciara del Fuoco.
The data are acquired by the monitoring network at a 50-Hz sampling frequency. The signals that are typically recorded include: volcanic tremor, as a continuous signal with a 1–3 Hz frequency range; explosion quakes, which have no distinct seismic phases and a 1–6 Hz frequency range; and landslides, with an emergent onset and a 1–10 Hz frequency range. Figure 2 shows a record of two and half hours at the STR8 station of the Stromboli network (the E-W horizontal component). On the seismogram, it is possible to distinguish some landslide signals (Fig. 2, red ellipses), explosion quakes (Fig. 2, red arrows) and background volcanic tremor (Fig. 2, blue rectangles). The landslide signals have a peculiar waveform, with a cigar-shaped amplitude envelope, and a spectral content higher than the typical explosion quakes and tremor signals. As we see below, these are the features that were considered during the parameterization phase, and then used by the neural net to identify landslides. In addition, other types of seismic signals are recorded, such as long-period earthquakes, rare volcano–tectonic earthquakes, VLP events (often associated with explosion quakes; Chouet et al., 2003), and teleseisms.
The dataset considered contains a total of 537 events recorded by four stations of the network (STRA, STRB, STR1, STR8; see Fig. 1) along the various components. Of these, 267 signals were classified as “landslide” and 270 as “other”, the latter of which included 130 explosion quakes and 140 tremor signals.
3 Data Parameterization
In the present study, we have set up a detector with a binary output, “landslide” or “other”, that is suitable for real-time analysis on sliding windows of incoming signals. As previously mentioned, the analysts can distinguish landslides from the other signals on seismograms due to their well-known frequency content and cigar-like waveform. The parameterization provides compact and robust signal encoding, and it appropriately describes the data. For each event, a 24-s-long recording is taken. As in Esposito et al. (2006), the spectral features are obtained by applying the linear predictive coding (LPC) technique (Makhoul, 1975), that gives the spectral envelope of a signal in compressed form. The LPC predicts a signal sample through a linear combination of its p previous samples:
where s (n) is the signal sample at time n, s*(n) is its prediction, and p is the model order, the value of which is problem dependent. The prediction coefficients c i , for i = 1,…, p, are estimated through an optimization procedure that reduces the error between the real signal and its LPC estimate. In our case, we extracted p = 6 LPC coefficients from each of the eight 5.12-s-long Hanning windows into which we divided the signals, with an overlap of 2.56 s. In this way, the LPC-spectrogram of each signal file is described by a vector of 48 spectral features.
The time-domain information of the signal is also preserved, through computing a function defined as the normalized difference between the maximum and minimum signal amplitudes within a 1-s long window. Thus for a 24-s long signal, a vector of 24 temporal elements is obtained.
As a result, the pre-processing returns a reduction in the initial file of 1,200 samples into a 72-element vector that is composed of 48 spectral coefficients, obtained from the LPC analysis, plus 24 time features, obtained from the waveform parameterization.
Figure 3 shows the parameterization of the signals belonging to the class “landslide” (panel A) and those in the class “other” (panel B), which contains explosion quakes and tremor signals. A seismogram is illustrated for each signal, along with the LPC-spectrogram and the vector of the 24 temporal features.
4 Landslide Detection
The landslide identification is performed by a MLP network (Bishop, 1995). The net structure includes: an input layer that receives the 72-dimensional vectors x i to be analyzed; a hidden layer and an output layer with a single neuron (Fig. 4).
The activation function of the hidden nodes is the hyperbolic-tangent expressed as:
while the output unit uses the logistic sigmoidal function computed as:
The net output y is calculated as:
where x i is the ith input unit, and W ij and w jk are the weights on the connections from the input to the hidden layer and from the hidden layer to the output layer, respectively. The output value ranges within [0–1], indicating the probability that the analyzed signal segment is a landslide.
The MLP carries out supervised learning using the quasi-Newton algorithm (Bishop, 1995), and performs a weight optimization through the minimization of the cross-entropy error function (Bishop, 1995), which for such a binary problem (“landslide/other” discrimination) is defined as:
where n is the number of training samples, t is the target vector, and y is the net output.
About 60 % of the total dataset is used to train the net, with events recorded by four stations (STRA, STRB, STR1, STR8; see Fig. 1) of the seismic network along the various components. The remaining events, different from those used for the training, are used for the testing. The percentage of correct classification of the network on the testing files is obtained by comparing the prediction vectors with the target ones (Young, 1993) and can be expressed as a percentage:
where N err is the number of signals do not correctly classified by the net and N tot is the total number of the testing signals.
Lastly, to validate the robustness of the net, we randomly changed the weight initialization and the data permutation. In this way the final network performance of 98.67 % was the average of the percentages of correct classification obtained with each experiment (Table 1) on the testing files.
5 Decision-Making Algorithm
To set up a method that can highlight changes in the landslide rate, the above described MLP is applied to analyze a 24-s-long sliding window that moves along the signal with an overlap of 12 s. For each window, the net calculates the probability that it contains a landslide signal. Because the net output ranges within [0–1], we fixed a threshold value of 0.95 to detect a landslide. This threshold is used to establish the beginning and the duration of the landslide. An example of the net response versus time for a typical landslide of about 2 min duration is illustrated in Fig. 5.
Then a landslide percentage index (LPI) is calculated, as the ratio between the number of windows that are classified as landslide and the total number of windows analyzed in a given time interval:
In particular, we chose a 10-min-long time interval of analysis, thus obtaining 49 signal windows, each one of 24 s with an overlap of 12 s.
The decision-making algorithm was applied in particular for the analysis of the data of February 27, 2007, which contains the beginning of the effusive eruption of Stromboli volcano. Moreover, for sake of simplicity, we will show the results of the MLP-based system only for the data recorded by the STR8 station, which is one of the closest to Sciara del Fuoco. Anyway the system could be implemented on any other station and temporal interval.
Figure 6 illustrates the seismogram of February 27, 2007, in which it is possible to observe the first landslide occurred at 08:57 UTC and the eruption onset at 12:39 UTC (Barberi et al., 2009; Giudicepietro et al., 2009; Ripepe et al., 2009).
In Fig. 7 the LPI over 10-min periods for the interval from January 1 to April 2, 2007, the end of the effusive phase, is shown. In particular, the LPI for the February 27, 2007 is visualized in the zoom window. Here, the solid red line indicates the eruption onset at 12:39 UTC, while the dashed red line in both graphs represents the pre-warning threshold value of the LPI. Observing the LPI for February 27, 2007, it can be noted that an increase in landslides is seen from 09:00 UTC, about 4 h before the onset of the eruption. Moreover, the neural algorithm highlights the occurrence of small landslides at around 06:00, which the analysts did not identified as such because of their relatively small amplitudes compared to those of tremor. After the beginning of the eruption, the landslide index also remained high during the lava flow phase on the Sciara del Fuoco side. This is due to the fact that the seismic signal source mechanism of the two processes, landslides and lava flow, is similar: in both cases the signal is due to rolling and sliding of blocks along the slope of Sciara del Fuoco.
Even if the aim of this work is to show the effectiveness of MLP networks in forecasting effusive eruptions at Stromboli, we believe they could be of more general interest. Landslides have shown to be a short-term precursor of effusive eruptions linked to brittle fracture of the volcano edifice with formation of eruptive fractures. Instead, if the lava flow is due to the overflow of lava without fracturing of the volcanic edifice, then the system can be used to track the activity of the lava front.
In this regard, Fig. 8 visualizes the LPI over 10-min periods for the interval from June 1 to August 31, 2011. The zoom window refers only to the days 1–2 August. In this range, the Stromboli monitoring network recorded two continuous high-frequency signals. The first one on August 1 at 20:52 UTC (solid red line A, Fig. 8), which lasted about 30 min, and the second one on August 2 at 04:14 UTC (solid red line B, Fig. 8), which lasted about 2 h. Both these signals were related to the movement of a small lava flow that was caused by an overflow from one of the summit craters (north vent). This type of lava flow, which typically involves small volumes, is different from those that occurred in 2003 and 2007 due to the opening of an eruptive fracture, and which was not preceded by unusual landsliding.
6 Conclusions
We have set up a landslide detector based on a supervised MLP network that is trained to distinguish between two classes of signals: “landslide” or “other”. Using the detector on a sliding window, it is possible to recognize not only the landslide occurrence, but also the start time and the duration of the seismic signal associated with the landslide. Our neural detector shows an averaged performance of correct classification of 98.67 %. Moreover, we have introduced an LPI, as defined in Sect. 5, that can be used as a decision-making tool for the recognition of anomalies in the landslide rate. The method we propose is based on the choice of a threshold value for the LPI. When this threshold is exceeded, a condition of instability is identified. In particular, from analyzing the case of the February 2007 Stromboli eruption, we would suggest a pre-warning threshold LPI value of 20 %, and would consider a warning as a continued LPI >20 % for more than a 30-min time period. We used the effusive eruption of 2007 as a case study because of the huge available dataset and because it is a typical effusive phase associated with the opening of an eruptive fissure. The data collected during this crisis have shown that the increase of landslide occurrence can be an important short-term precursor of this type of phenomena. The observation made in a period of about 9 years have also enabled us to highlight that lava flows due to overflow from the summit craters are not preceded by a significant increase in the occurrence rate of landslides and typically involve smaller volumes of lava. In this case, our analysis allows to highlight the seismic signals caused by rolling blocks that fall from the lava front and then to trace the activity of the lava flow.
In the future, the proposed decision-making method regarding the recognition of the precursor “increase in landslide rate” will be integrated into the real-time monitoring system of Stromboli. The latter is composed of several modules for automatic analysis of the seismic data, some of which make use of parallel computing techniques (Auger et al., 2006; D’Auria et al., 2004). All of the data processed in real time are available on the system named “EOLO” at the internet address http://eolo.ov.ingv.it/. This system shows that before the last effusive phase at Stromboli, in addition to the increase in the landslide rate that occurred from a few hours before the beginning of the effusive eruption, there were other changes that occurred in the seismicity of the Stromboli volcano from several days before the effusive eruption. These included an increase in the occurrence rate and amplitude of the VLP, changes in the polarization parameters, and an increase in the seismic amplitude (Martini et al., 2007). Therefore, in the future we aim to develop an integrated system for the recognition of all of the seismic precursors, to obtain a more meaningful tool for decision making relating to the state of Stromboli volcano.
References
Auger E., D’Auria L., Martini M., Chouet B., Dawson P. (2006) Real-time monitoring and massive inversion of source parameters of very long period seismic signals: An application to Stromboli Volcano, Italy, Geoph. Res. Lett. Vol. 33, L04301, doi:10.1029/2005GL024703.
Barberi F., Civetta L., Rosi M., Scandone R. (2009) Chronology of the 2007 eruption of Stromboli and the activity of the Scientific Synthesis Group, Journal of Volcanology and Geothermal Research, Vol. 182 (2009), 123–130.
Baldi P., Fabris M., Marsella M., Monticelli R. (2005) Monitoring the morphological evolution of the Sciara del Fuoco during the 2002–2003 Stromboli eruption using multi-temporal photogrammetry, ISPRS Journal of Photogrammetry & Remote Sensing 59 (2005) 199–211.
Barabino N., Pallavicini M., Petrolini A., Pontil M., Verri A. (1999) Support Vector Machines vs Multi-Layer Perceptron in Particle Identification, ESANN’1999 proceedings—European Symposium on Artificial Neural Networks Bruges (Belgium), 21-23 April 1999, D-Facto public., ISBN 2-600049-9-X, pp. 257–262.
Bishop C. (1995) Neural Networks for pattern recognition, Oxford University Press. 500 pp.
Calvari S., Spampinato L., Lodato L., Harris A.J.L., Patrick M.R., Dehn J., Burton M.R. and Andronico D. (2005) Chronology and complex volcanic processes during the 2002-2003 flank eruption at Stromboli volcano (Italy) reconstructed from direct observations and surveys with a handheld thermal camera, J. Geoph. Res., Vol. 110, B02201, doi:10.1029/2004JB003129.
Casagli N., Tibaldi A., Merri A., Del Ventisette C., Apuani T., Guerri L., Fortuny-Guasch J., Tarchi D. (2009) Deformation of Stromboli Volcano (Italy) during the 2007 eruption revealed by radar interferometry, numerical modelling and structural geological field data, Journal of Volcanology and Geothermal Research 182 (2009) 182–200, Elsevier B.V., doi:10.1016/j.jvolgeores.2009.01.002.
Cercone J.M. and Martin J.R. (1994) An application of neural networks to seismic signal discrimination, Phillips Laboratory, report no. 3, PL-TR-94-2178, Hanscon, AFB, Massachusetts.
Chouet B., Dawson P., Ohminato T., Martini M., Saccorotti G., Giudicepietro F., De Luca G., Milana G. and Scarpa R. (2003) Source mechanisms of explosions at Stromboli Volcano, Italy, determined from moment-tensor inversions of very-long-period data, J. Geoph. Res., Vol. 108 (B1).
D’Auria L., Giudicepietro F., Martini M. and Peluso R. (2006) Seismological insight into the kinematics of the 5 April 2003 vulcanian explosion at Stromboli volcano (Southern Italy), Geophys. Res. Lett., Vol. 33, L08308, doi:10.1029/2006GL026018.
D’Auria L., Martini M., Auger E., Giudicepietro F., De Cesare W., Scarpato G. (2004) The EOLO system for automatic seismic monitoring of Stromboli, Incontro scientifico: L’eruzione di Stromboli (28 Dicembre 2002-20 Luglio 2003), Catania, 20-21 Maggio 2004.
De Cesare W., Orazi M., Peluso R., Scarpato G., Caputo A., D’Auria L., Giudicepietro F., Martini M., Buonocunto C., Capello M., Esposito A. M. (2009) The broadband seismic network of Stromboli volcano, Italy, Seismol. Res. Lett., Vol. 80, 435–439, doi:10.1785/gssrl.80.3.435.
Del Pezzo E., Esposito A., Giudicepietro F., Marinaro M., Martini M. and Scarpetta S. (2003) Discrimination of earthquakes and underwater explosions using neural networks, Bull. Seism. Soc. Am. 93, 215–223.
Dowla F.U., Taylor S.R. and Anderson R.W. (1990) Seismic discrimination with artificial neural networks: preliminary results with regional spectral data, Bull. Seism. Soc. Am. 80, 1346–1373.
Dowla F.U. (1995) Neural networks in seismic discrimination, in Monitoring a Comprehensive Test Ban Treaty, E.S. Husebye and A.M. Dainty (Editors), NATO ASI, Series E, 303, Kluwer, Dordrecht, The Netherlands, 777–789.
Hartse H. E., Phillips W. S., Fehler M. C., and House L. S. (1995) Single-station spectral discrimination using coda waves, Bull. Seism. Soc. Am. 85, 1464–1474.
Esposito A. M., Giudicepietro F., Scarpetta S., D’Auria L., Marinaro M., Martini M. (2006) Automatic discrimination among landslide, explosion-quake and microtremor seismic signals at Stromboli volcano using neural networks, Bull. Seismol. Soc. Am. 96, 1230–1240, doi:10.1785/0120050097.
Falsaperla S., Neri M., Pecora E., Spampinato S. (2006) Multidisciplinary study of flank instability phenomena at Stromboli volcano, Italy, Geoph. Res. Lett., Vol. 33, L09304, 4 PP., doi:10.1029/2006GL025940.
Giacco F., Esposito A.M., Scarpetta S., Giudicepietro F. and Marinaro M. (2009) Support Vector Machines and MLP for automatic classification of seismic signals at Stromboli volcano, in Neural Nets WIRN09 Proceedings of the 19th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, May 28-30, 2009, B. Apolloni et al. (Eds.), IOS Press, 2009.
Gitterman Y., Pinky V., and Shapira A. (1999) Spectral discrimination analysis of Eurasian nuclear tests and earthquakes recorded by the Israel seismic network and the NORESS array, Phys. Earth. Planet. Interiors 113, 111–129.
Giudicepietro F., D’Auria L., Martini M., Caputo T., Peluso R., De Cesare W., Orazi M., Scarpato G. (2009) Changes in the VLP seismic source during the 2007 Stromboli eruption, Journal of Volcanology and Geothermal Research Vol. 182 (2009), 162–171, doi:10.1016/j.jvolgeores.2008.11.008.
Joswig M. (1990) Pattern recognition for earthquake detection, Bull. Seism. Soc. Am. 80, 170–186.
Langer H., Falsaperla S., Masotti M., Campanini R., Spampinato S. (2009) Synopsis of supervised and unsupervised pattern classification techniques applied to volcanic tremor data atMt Etna, Italy, Geophys. J. Int. (2009) 178, 1132–1144, doi:10.1111/j.1365-246X.2009.04179.x.
La Rocca M., Galluzzo D., Saccorotti G., Tinti S., Cimini G. B. and Del Pezzo E. (2004) Seismic Signals Associated with Landslides and with a Tsunami at Stromboli Volcano, Italy, Bull. Seismol. Soc. Am. 94, no. 5, 1850–1867, doi:10.1785/012003238.
Makhoul J. (1975) Linear prediction: a tutorial review, Proc. IEEE 63, 561–580.
Martini M., Giudicepietro F., D’Auria L., Esposito A.M., Caputo T., Curciotti R., De Cesare W., Orazi M., Scarpato G., Caputo A., Peluso R., Ricciolino P., Linde A., Sacks S. (2007) Seismological monitoring of the February 2007 effusive eruption of the Stromboli volcano, Ann. Geophys. Vol. 50, N. 6, 775–788.
Masotti M., Falsaperla S., Langer H., Spampinato S., and Campanini R. (2006) Application of Support Vector Machine to the classification of volcanic tremor at Etna, Italy, Geophys. Res. Lett., 33, L20304, doi:10.1029/2006GL027441.
Nunnari G., Puglisi G. and Spata A. (2008) A Warning System for Stromboli Volcano Based on Statistical Analysis, Pure appl. geophys. 165 (2008) 1619–1641, 0033-4553/08/081619-23, Birkha¨user Verlag, Basel, 2008, doi:10.1007/s00024-008-0392-y.
Osowski S., Siwek K., Markiewicz T. (2004) MLP and SVM networks: a comparative study, Proceedings of the Nordic Signal Processing Symposium—NORSIG 2006—NORSIG, 2004, doi:10.1109/NORSIG.2004.250120.
Pino N. A. and Boschi E. (2009) Seismic detection of island trapped sea waves from a landslide-generated tsunami at Stromboli (Italy), Geophysical Research Letters, Vol. 36, L09305, doi:10.1029/2009GL037550.
Puglisi G., A. Bonaccorso, M. Mattia, M. Aloisi, A. Bonforte, O. Campisi, M. Cantarero, G. Falzone, B. Puglisi, M. Rossi (2005) New integrated geodetic monitoring system at Stromboli volcano (Italy), Engineering Geology 79 (2005) 13-31, Published by Elsevier B.V., doi:10.1016/j.enggeo.2004.10.013.
Ripepe M., Delle Donne D., Lacanna G., Marchetti E., Ulivieri G. (2009) The onset of the 2007 Stromboli effusive eruption recorded by an integrated geophysical network, Journal of Volcanology and Geothermal Research, Vol. 182 (2009), 131–136.
Rowe C. A., Thurber C. H., and White R. A. (2004). Dome growth behaviour at Soufriere Hills volcano, Montserrat, revealed by relocation of volcanic event swarms, 1995–1996, J. Volc. Geotherm. Res. 134, 199–221.
Scarpetta S., Giudicepietro F., Ezin E.C., Petrosino S., Del Pezzo E., Martini M. and Marinaro M. (2005) Automatic Classification of seismic signals at Mt. Vesuvius Volcano, Italy using Neural Networks, Bull. Seism. Soc. Am., Vol. 95, 185–196.
Schffolkopf, B. and Smola A.J. (2002) Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond, MIT Press.
Tibaldi A. (2001) Multiple sector collapses at stromboli volcano, Italy: how they work, Bulletin of Volcanology Vol. 63, N. 2-3, 112–125, doi:10.1007/s004450100129.
Tiira T. (1999) Detecting teleseismic events using artificial neural networks, Comp. Geosci. Vol. 25, 929–939.
Tinti S., Manucci A., Pagnoni G., Armigliato A., Zaniboni F. (2005) The 30 December 2002 landslide-induced tsunamis in Stromboli: sequence of the events reconstructed from the eyewitness accounts, Natural Hazards and Earth System Science 5, 6 (2005) 763–775.
Tinti S., Pagnoni G. and Zaniboni F. (2006) The landslides and tsunamis of the 30th of December 2002 in Stromboli analysed through numerical simulations, Bulletin of Volcanology Vol. 68, N. 5, 462–479, doi:10.1007/s00445-005-0022-9.
Wang J. and Teng T. (1995) Artificial neural network based seismic detector, Bull. Seism. Soc. Am. Vol. 85, 308–319.
Young S. J. (1993) HTK: Hidden Markov Model Toolkit V1.5, Cambridge University Engineering Department Speech Group and Entropic Research Laboratories, Inc., Washington, D.C.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Esposito, A.M., D’Auria, L., Giudicepietro, F. et al. Automatic Recognition of Landslides Based on Neural Network Analysis of Seismic Signals: An Application to the Monitoring of Stromboli Volcano (Southern Italy). Pure Appl. Geophys. 170, 1821–1832 (2013). https://doi.org/10.1007/s00024-012-0614-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00024-012-0614-1