Multi-geophysical parameter classification of the Montserrat geothermal system

“…Cluster analysis is an important unsupervised machine learning method used to study classification problems (Steinhaus, 1956;Ball and Hall, 1965;Bosch, 1999;Bedrosian et al, 2007). By measuring the similarity between attributes in the feature space, it enables automatic, objective, and quantitative analysis of multi-source geophysical data sets (Fraser et al, 2012;Di Giuseppe et al, 2018;Melo and Li, 2019;Basant et al, 2021;Ali et al, 2021). Partition-based clustering methods, in particular, are widely used in the field of Earth sciences due to their advantages of simplicity, efficiency, ability to handle large-scale datasets, and interpretability of results (Ali et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

3D pseudo-lithologic modeling via iterative weighted k-means++ algorithm from Tengger Desert cover area, China

et al. 2023

View full text Add to dashboard Cite

The bedrock beneath the Tengger Desert is covered by Quaternary deposits, making it difficult to directly observe the underlying geological information using traditional geological methods. In areas with limited prior geological information, employing geophysical methods to obtain deep-seated information, constructing a multi-source geophysical dataset, and performing three-dimensional modeling can significantly enhance our understanding of the underground geological structures. Cluster analysis is a fundamental unsupervised machine learning technique employed in data mining to investigate the data structure within the feature space. This paper proposes an iterative weighted distance-based extension to the k-means clustering algorithm, referred to as the Iterative Weighted Distance K-means (IW k-means++) algorithm. It incorporates the farthest distance method to select the initial centroid, performs iterative centroid updates based on weighted distance, and dynamically adjusts feature weights during training. The Davies-Bouldin index shows that the performance of IW k-means ++ clustering algorithm is better than the traditional K-Meme ++ clustering algorithm in 3D pseudo-lithology modeling.

show abstract

“…Joint interpretation of tomographic and geophysical models can better constrain interpretations of a volcanic structure. In recent works (e.g., Basant et al., 2021; Cordell et al., 2020; De Siena et al., 2017; García‐Yeguas et al., 2017), the integration of different geophysical models has highlighted important structures for different volcanic scenarios. Here, we compared our attenuation tomography results with geophysical models—two P wave seismic tomographies (Díaz‐Moreno et al., 2018; Giampiccolo et al., 2020) and a 3D coda waves seismic attenuation model (Giampiccolo et al., 2021)—and the literature to highlight and interpret structural elements and their role in volcano dynamics at Mt.…”

Section: Introductionmentioning

confidence: 99%

Shallow Magma Storage Beneath Mt. Etna: Evidence From New Attenuation Tomography and Existing Velocity Models

et al. 2021

View full text Add to dashboard Cite

Determining the location and size of potential magma reservoirs is crucial to constrain the size of future eruptions or eruptive frequency. Magma accumulation and melt migration have been the focus of extensive research at Mt. Etna volcano. Recent geophysical imaging of Mt. Etna has shown the growing importance of several geological bodies in explaining the migration of eruptive materials inside the volcano. One such body, known as the High Velocity Body (HVB), is a highly consolidated structure located below the central-southern part of the volcano. The HVB has been observed in several tomography studies (Giampiccolo et al., 2020 and references therein) and is interpreted as a massive accumulation of intrusions within the sedimentary basement. In addition, new structural elements have been identified tomographically to the west and southwest of the main volcanic edifice (e.g., Díaz-Moreno et al., 2018 and references therein). Despite not being widely discussed and interpreted in studies based on travel time tomography, these bodies have been well resolved using other techniques. In addition, recent studies (Alparone et al., 2015;Barberi et al., 2016) have found a strong association between deep seismicity beneath Mt. Etna and these geological objects, indicating the need for further study. Apparent contradictions between older and newer tomographic images possibly reflect the increased sensitivity of new tomography techniques to rock heterogeneity

show abstract

Multi-geophysical parameter classification of the Montserrat geothermal system

Cited by 6 publications

References 32 publications

COVID-19 ground-glass opacity segmentation based on fuzzy c-means clustering and improved random walk algorithm

COVID-19 ground-glass opacity segmentation based on fuzzy c-means clustering and improved random walk algorithm

3D pseudo-lithologic modeling via iterative weighted k-means++ algorithm from Tengger Desert cover area, China

Shallow Magma Storage Beneath Mt. Etna: Evidence From New Attenuation Tomography and Existing Velocity Models

Contact Info

Product

Resources

About