Insights Into Microseism Sources by Array and Machine Learning Techniques: Ionian and Tyrrhenian Sea Case of Study

Abstract

In this work, we investigated the microseism recorded by a network of broadband seismic stations along the coastline of Eastern Sicily. Microseism is the most continuous and ubiquitous seismic signal on Earth and is mostly generated by the ocean-solid earth interaction. On the basis of spectral content, it is possible to distinguish three types of microseism: primary, secondary, and short-period secondary microseism (SPSM). We showed how most of the microseism energy recorded in Eastern Sicily is contained in the secondary and SPSM bands. This energy exhibits strong seasonal patterns, with maxima during the winters. By applying array techniques, we observed how the SPSM sources are located in areas of extended shallow water depth: the Catania Gulf and a part of the Northern Sicily coastlines. Finally, by using the significant wave height data recorded by two buoys installed in the Ionian and Tyrrhenian Seas, we developed an innovative method, selected among up-to-date machine learning techniques (MLTs), able to reconstruct the time series of sea wave parameters from microseism recorded in the three microseism period bands by distinct seismic stations. In particular, the developed model, based on random forest regression, allowed estimating the significant wave height with a low average error (∼0.14-0.18 m). The regression analysis suggests that the closer the seismic station to the sea, the more information concerning the sea state are contained in the recorded microseism. This is particularly important for the future development of an experimental monitoring system of the sea state conditions based on microseism recordings.

Sea Wave Data Reconstruction Using Micro-Seismic Measurements and Machine Learning Methods

“…For example, the micro-seismic station used for this work was specifically installed close to the shoreline and in front of the buoy of La Spezia (see Figure 2). As demonstrated in Moschella et al (2020), this displacement of the instrumentation leads to more accurate buoy data reconstruction. In fact, undesired signals, such as those from remote seismic sources, are less relevant and the signal to noise ratio is higher than that of stations far away from the shoreline and the reference buoy.…”

“…In Cannata et al (2020), a machine learning method (specifically, a random forest) was proposed to reconstruct the spatial distribution of sea wave height, as provided by hindcast maps of sea wave models, by using micro-seismic data from multiple seismic stations. In Moschella et al (2020), a network of broadband seismic stations was used to investigate the microseismic signals from Ionian and Tyrrhenian Sea and, importantly, it was demonstrated that the signal detected by seismic stations closer to the sea contain more information concerning the sea state than the others.…”

Achievements and Prospects of Global Broadband Seismographic Networks After 30 Years of Continuous Geophysical Observations

“…Relative and absolute ocean wave metrics can be extracted from the microseism wavefield (Bromirski & Duennebier, 2002; Bromirski & Flick, 2020; Moschella et al., 2020) and wave effects due to variations in climate indices, sea ice, and other environmental drivers can be discerned across decade‐scale time periods using data from long‐duration globally distributed seismographic stations (Anthony, Aster, & McGrath, 2017; Aster et al., 2010; Tsai & McNamara, 2011). The data quality and long‐running history of GSNs and the prominent generation of microseism signals has been exploited to examine hurricanes, typhoons, and other extreme storm events (Ebeling & Stein, 2011; Gerstoft et al., 2006; Retailleau & Gualtieri, 2019) across the world's oceans over the last 30 years, as well as decade‐scale secular changes in ocean wave intensity and location (Aster et al., 2008, 2010; Grevemeyer et al., 2000), and interactions between climate indices, ocean state, and the cryosphere (sea ice) (Anthony, Aster, & McGrath, 2017; Cannata et al., 2019).…”

Measurement of Sea Waves

“…Finally, several authors have explored the ability of microseism analysis to provide quantitative information on the sea state, mainly in terms of sea wave height [ 171 , 186 , 187 , 188 , 189 , 190 , 191 , 192 ]. Bromirski et al [ 187 ] analyzed buoy and seismometer data collected during the period 1997–1998 in California and derived site-specific seismic-to-wave transfer functions.…”

“…In addition, the locations of the microseism sources can be difficult to determine, and so the wave parameters in a given location in the sea can be difficult to define. This second issue can be solved using multiple sparse stations [ 192 , 196 ] or station arrays (that is, a certain number of seismic stations placed at discrete points in a well-defined configuration [ 197 , 198 ]).…”