当前位置: X-MOL 学术Comput. Geosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Analyzing continuous infrasound from Stromboli volcano, Italy using unsupervised machine learning
Computers & Geosciences ( IF 4.2 ) Pub Date : 2020-07-01 , DOI: 10.1016/j.cageo.2020.104494
Alex J.C. Witsil , Jeffrey B. Johnson

Abstract Infrasound data are used by scientists and monitoring observatories to track shifts in eruptive behavior, identify signs of unrest, and ultimately help forecast major eruptions. However, infrasound analyses are often limited to a catalog of discrete or high-amplitude transient events, which can leave lower-amplitude emergent or continuous signals within the datastream unexplored. This study classifies continuous volcano infrasound data using unsupervised learning in order to better constrain eruptive behavior through time. Data were recorded from 9 through 12 September (2018) at Stromboli, Italy by three infrasound arrays sampling at 200 Hz and deployed within 400 m of the active vents. Recorded pressure amplitudes were synthesized into a set of characteristic features extracted from the time and frequency domains of five second overlapping windows. Features were then clustered via the k-means algorithm resulting in a time-series of discrete labels that track the evolutionary behavior during the three-day experiment. Waveforms associated with each cluster relate to commonly recorded volcanic signals including Strombolian events, puffing activity, and sustained degassing associated with acoustic tremor. Infrasound radiated predominantly from six vent regions, each of which exhibit temporal variability in their degassing behavior. The three-day history of activity reveals an exchange of function across multiple vents indicating potential linkages in the plumbing system.

中文翻译:

使用无监督机器学习分析来自意大利斯特龙博利火山的连续次声

摘要 科学家和监测天文台使用次声数据来跟踪喷发行为的变化,识别动荡的迹象,并最终帮助预测重大喷发。然而,次声分析通常仅限于离散或高振幅瞬态事件的目录,这可能会使数据流中的低振幅突发或连续信号无法探索。本研究使用无监督学习对连续的火山次声数据进行分类,以便更好地随着时间的推移限制喷发行为。数据于 2018 年 9 月 9 日至 12 日在意大利斯特龙博利通过三个次声阵列以 200 Hz 采样并部署在活动通风口 400 m 内记录。记录的压力幅度被合成为一组从五秒重叠窗口的时域和频域中提取的特征。然后通过 k-means 算法对特征进行聚类,产生一个离散标签的时间序列,这些标签在为期三天的实验中跟踪进化行为。与每个集群相关的波形与通常记录的火山信号有关,包括 Strombolian 事件、喷发活动和与声震相关的持续脱气。次声主要从六个喷口区域辐射,每个喷口区域的脱气行为都表现出时间变化。三天的活动历史揭示了多个通风口之间的功能交换,表明管道系统中存在潜在的联系。然后通过 k-means 算法对特征进行聚类,产生一个离散标签的时间序列,这些标签在为期三天的实验中跟踪进化行为。与每个集群相关的波形与通常记录的火山信号有关,包括 Strombolian 事件、喷发活动和与声震相关的持续脱气。次声主要从六个喷口区域辐射,每个喷口区域的脱气行为都表现出时间变化。三天的活动历史揭示了多个通风口之间的功能交换,表明管道系统中存在潜在的联系。然后通过 k-means 算法对特征进行聚类,产生一个离散标签的时间序列,这些标签在为期三天的实验中跟踪进化行为。与每个集群相关的波形与通常记录的火山信号有关,包括 Strombolian 事件、喷发活动和与声震相关的持续脱气。次声主要从六个喷口区域辐射,每个喷口区域的脱气行为都表现出时间变化。三天的活动历史揭示了多个通风口之间的功能交换,表明管道系统中存在潜在的联系。与每个集群相关的波形与通常记录的火山信号有关,包括 Strombolian 事件、喷发活动和与声震相关的持续脱气。次声主要从六个喷口区域辐射,每个喷口区域的脱气行为都表现出时间变化。三天的活动历史揭示了多个通风口之间的功能交换,表明管道系统中存在潜在的联系。与每个集群相关的波形与通常记录的火山信号有关,包括 Strombolian 事件、喷发活动和与声震相关的持续脱气。次声主要从六个喷口区域辐射,每个喷口区域的脱气行为都表现出时间变化。三天的活动历史揭示了多个通风口之间的功能交换,表明管道系统中存在潜在的联系。
更新日期:2020-07-01
down
wechat
bug