Recognizing explosion sites with a self-organizing network for unsupervised learning

Tarvainen, Matti

doi:10.1016/s0031-9201(99)00019-9

Cited by 18 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We apply the Self-Organizing Map (SOM) technique, a quasi-artificial, unsupervised neural network used to intuitively visualize and cluster multidimensional data (Kohonen, 2001), which has been successfully applied for pattern recognition in seismology (Maurer et al, 1992;Musil and Plešinger, 1996;Tarvainen, 1999;Plešinger et al, 2000;Esposito et al, 2008;Köhler et al, 2010). The main property of SOMs is that data can be mapped on a two-dimensional, regular grid of usually hexagonal SOM units.…”

Section: Seismic Event Clusteringmentioning

confidence: 99%

Autonomous detection of calving-related seismicity at Kronebreen, Svalbard

et al. 2012

View full text Add to dashboard Cite

Abstract. We detect and cluster waveforms of seismic signals recorded close to the calving front of Kronebreen, Svalbard, to identify glacier-related seismic events and to investigate their relation to calving processes. Single-channel geophone data recorded over several months in 2009 and 2010 are combined with eleven days of direct visual observations of the glacier front. We apply a processing scheme which combines conventional seismic event detection using a sensitive trigger algorithm and unsupervised clustering of all detected signals based on their waveform characteristics by means of Self-Organizing Maps (SOMs). About 10 % of the directly observed calving events close to the geophone (<1 km) can be correlated with seismic detections. We are able to distinguish between false detections, instrumental artifacts, and three classes of signals which are, with different degrees of uncertainty, emitted by calving or glacier activity in general. By extrapolating the interpretation of seismic event classes beyond the time period of visual observations, the temporal distribution of glacier-related events shows an increase in event rate in autumn, particularly for the class which is related to iceberg calving. Using the seismic event distribution in this class as a proxy for the calving rate and measurements of glacier velocity and glacier front position, we discuss the possible relationship between glacier dynamics and calving processes at Kronebreen.

show abstract

Section: Seismic Event Clusteringmentioning

confidence: 99%

Autonomous detection of calving-related seismicity at Kronebreen, Svalbard

et al. 2012

View full text Add to dashboard Cite

show abstract

“…SOMs have already been applied, in different contexts, for active seismic data sets (Essenreiter et al 2001; Klose 2006; De Matos et al 2007) and in seismology (Maurer et al 1992; Musil & Plešinger 1996; Tarvainen 1999; Plešinger et al 2000; Esposito et al 2008; Köhler et al 2009). The latter studies employed SOMs for event discrimination (e.g.…”

Section: Methodsmentioning

confidence: 99%

Unsupervised pattern recognition in continuous seismic wavefield records using Self-Organizing Maps

Köhler¹,

Ohrnberger

Scherbaum

2010

Geophysical Journal International

107

View full text Add to dashboard Cite

S U M M A R YModern acquisition of seismic data on receiver networks worldwide produces an increasing amount of continuous wavefield recordings. In addition to manual data inspection, seismogram interpretation requires therefore new processing utilities for event detection, signal classification and data visualization. The use of machine learning techniques automatises decision processes and reveals the statistical properties of data. This approach is becoming more and more important and valuable for large and complex seismic records. Unsupervised learning allows the recognition of wavefield patterns, such as short-term transients and long-term variations, with a minimum of domain knowledge. This study applies an unsupervised pattern recognition approach for the discovery, imaging and interpretation of temporal patterns in seismic array recordings. For this purpose, the data is parameterized by feature vectors, which combine different real-valued wavefield attributes for short time windows. Standard seismic analysis tools are used as feature generation methods, such as frequency-wavenumber, polarization and spectral analysis. We use Self-Organizing Maps (SOMs) for a data-driven feature selection, visualization and clustering procedure. The application to continuous recordings of seismic signals from an active volcano (Mount Merapi, Java, Indonesia) shows that volcanotectonic and rockfall events can be detected and distinguished by clustering the feature vectors. Similar results are obtained in terms of correctly classifying events compared to a previously implemented supervised classification system. Furthermore, patterns in the background wavefield, that is the 24-hr cycle due to human activity, are intuitively visualized by means of the SOM representation. Finally, we apply our technique to an ambient seismic vibration record, which has been acquired for local site characterization. Disturbing wavefield patterns are identified which affect the quality of Love wave dispersion curve estimates. Particularly at night, when the overall energy of the wavefield is reduced due to the 24-hr cycle, the common assumption of stationary planar surface waves can be violated.

show abstract

“…As equações (1), (2) e (7) são à base de vários algoritmos que utilizam funções de custo para agrupamento orientados à média, dentre eles o SOM de Kohonen [15] [16] [17]. Este método é freqüentemente utilizado para agrupamento de dados sísmicos [18] [19] [20]. No entanto, os métodos de agrupamento que tratam distribuições assimétricas (caso dos dados sísmicos) são evidentemente menos eficientes se utilizam médias como estimador do centro dos grupos formados [21] [22].…”

Section: Agrupamento E Visualização De Dados Sísmicos Através De Quanunclassified

Agrupamento e visualização de dados sísmicos através de quantização vetorial

Fleck¹,

Pedreira²,

Santos³

2016

Anais Do 7. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

This work suggests the use of a new method of seismic data clustering that can aid in the visualizati on of seismic maps. Seismic data have asymmetric distributions. They are traditionally classified by methods that lead the proposed groups' references to their mean values. The mean value is, however, sensitive to noise and outliers and the classification methods that make use of this estimator are, consequently, subjected to generating distorted results. Although other works have suggested the use of the median in cases where the distributions are asymmetric -due to the fact that the estimator is robust with respect to noise and outliers -none have proposed a method that would lead the groups' references to the median while treating seismic data.Palavras chaves-Agrupamento de dados, m apas s ísmicos, mediana, quantização vetorial, tratamento de distribuições assimétricas. I. INTRODUÇÃOA determinação da dimensão de reservatórios de petróleo é um importante desafio para a indústria de hidrocarbonetos. Em geral, a estrutura destes reservatórios é geologicamente complexa devido, entre outros fatores, às descontinuidades das estruturas que unem as áreas de grande concentração de petróleo. Os maiores desafios acontecem quando ocorrem estruturas de pequenas espessuras [1]. Tradicionalmente, uma ferramenta essencial para o dimensionamento dos reservatórios são os m apas sísmicos que realçam as formas geológicas encontradas. Com o aumento da potencialidade dos recursos computacionais, a evolução dos mapas de dados sísmicos adquiriu novas possibilidades e pode ser resumida da seguinte forma: (a) Mapas que evidenciam, e m cores, contrastes de faixas de valores dos dados sísmicos atribuídas pelo geofísico. Nestes casos, os mapas dependem do conhecimento do intérprete que determina faixas associadas a cores para a definição de estruturas. O sucesso da pesquisa depende de c onsiderável tempo de dedicação de um profissional altamente qualificado; (b) Mapas que mostram formas geológicas resultantes de processos de agrupamento de dados sísmicos, realizados através de técnicas de inteligência computacional. A opção b tem mostrado melhores resultados [2]. No entanto, os grupos formados por vezes não atendem satisfatoriamente às necessidades de visualização das formas geológicas mais complexas desejadas pelos geofísicos. O entendimento da não satisfação está relacionado às características dos dados sísmicos pouco consideradas nas suas classificações pelos métodos existentes [3] [4] [5]. Em um método de agrupamento de dados sísmicos, espera-se que um tratamento do sinal determine, pelo menos, formas estruturais (falhas, bordas, dunas, diques...) e formas estratigráficas (canais, lobos, leques, barras,...). A média e a mediana são dois estimadores de posição possíveis. A escolha de um destes estimadores pode influenciar na determinação dos grupos estudados. Normalmente, os dados sísmicos distribuem-se assimetricamente e uma conseqüência desta assimetria é a desigualdade de valores entre a média e a mediana da distribuição dos dados. ...

show abstract

Recognizing explosion sites with a self-organizing network for unsupervised learning

Cited by 18 publications

References 17 publications

Autonomous detection of calving-related seismicity at Kronebreen, Svalbard

Autonomous detection of calving-related seismicity at Kronebreen, Svalbard

Unsupervised pattern recognition in continuous seismic wavefield records using Self-Organizing Maps

Agrupamento e visualização de dados sísmicos através de quantização vetorial

Contact Info

Product

Resources

About