Repeated periods of inflation‐deflation in the vicinity of Mt. Thorbjorn‐Svartsengi, SW‐Iceland, were detected in January–July, 2020. We used seismic ambient noise and interferometry to characterize temporal variations of seismic velocities (dv/v, %). This is the first time in Iceland that dv/v variations are monitored in near real‐time during volcanic unrest. The seismic station closest to the inflation source center (∼1 km) showed the largest velocity drop (∼ 1%). Different frequency range measurements, from 0.1 to 2 Hz, show dv/v variations, which we interpret in terms of varying depth sensitivity. The dv/v correlates with deformation measurements (GPS, InSAR), over the unrest period, indicating sensitivity to similar crustal processes. We interpret the velocity drop to be caused by crack opening triggered by intrusive magmatic activity. We conclude that single‐station cross‐component analyses provide the most robust solutions for early detection of magmatic activity.

Seismologists working with fiber-optic sensing, commonly referred to as Distributed Acoustic Sensing (DAS), have yet to find an established way of automatically detecting signals of interest within its recordings. We propose a new research perspective within the field by examining the output of a DAS array as an image and processing the image to find signals of interest. In this manuscript, we show an example of such a method, where we automatically detect seismic events of interest within two different DAS datasets, finding, respectively 99 % and 96 % of the local earthquakes previously identified within the data by manual analysis. The method is based on simple image processing and computer vision techniques, which clean the image, and, ideally, leave nothing but the signal of interest. These simple image processing steps yield promising results, indicating that computer vision and image processing might have an immediate impact in geophysical applications of fiber-optic sensing.