Search for: All records

An increase in volcanic thermal emissions can indicate subsurface and surface processes that precede, or coincide with, volcanic eruptions. Space-borne infrared sensors can detect hotspots—defined here as localized volcanic thermal emissions—in near-real-time. However, automatic hotspot detection systems are needed to efficiently analyze the large quantities of data produced. While hotspots have been automatically detected for over 20 years with simple thresholding algorithms, new computer vision technologies, such as convolutional neural networks (CNNs), can enable improved detection capabilities. Here we introduce HotLINK: the Hotspot Learning and Identification Network, a CNN trained to detect hotspots with a dataset of −3,800 satellite-based, Visible Infrared Imaging Radiometer Suite (VIIRS) images from Mount Veniaminof and Mount Cleveland volcanoes, Alaska. We find that our model achieves an accuracy of 96% (F1-score 0.92) when evaluated on −1,700 unseen images from the same volcanoes, and 95% (F1-score 0.67) when evaluated on −3,000 images from six additional Alaska volcanoes (Augustine Volcano, Bogoslof Island, Okmok Caldera, Pavlof Volcano, Redoubt Volcano, Shishaldin Volcano). In comparison with an existing threshold-based hotspot detection algorithm, MIROVA (Coppola et al., Geological Society, London, Special Publications, 2016, 426, 181–205), our model detects 22% more hotspots and produces 12% fewer false positives. Additional testing on −700 labeled Moderate Resolution Imaging Spectroradiometer (MODIS) images from Mount Veniaminof demonstrates that our model is applicable to this sensor’s data as well, achieving an accuracy of 98% (F1-score 0.95). We apply HotLINK to 10 years of VIIRS data and 22 years of MODIS data for the eight aforementioned Alaska volcanoes and calculate the radiative power of detected hotspots. From these time series we find that HotLINK accurately characterizes background and eruptive periods, similar to MIROVA, but also detects more subtle warming signals, potentially related to volcanic unrest. We identify three advantages to our model over its predecessors: 1) the ability to detect more subtle volcanic hotspots and produce fewer false positives, especially in daytime images; 2) probabilistic predictions provide a measure of detection confidence; and 3) its transferability, i.e., the successful application to multiple sensors and multiple volcanoes without the need for threshold tuning, suggesting the potential for global application. 

Real-time monitoring is crucial to assess hazards and mitigate risks of sustained volcanic eruptions that last hours to months or more. Sustained eruptions have been shown to produce a low frequency (infrasonic) form of jet noise. We analyze the lava fountaining at fissure 8 during the 2018 Lower East Rift Zone eruption of Kīlauea volcano, Hawaii, and connect changes in fountain properties with recorded infrasound signals from an array about 500 m from the fountain using jet noise scaling laws and visual imagery. Video footage from the eruption reveals a change in lava fountain dynamics from a tall, distinct fountain at the beginning of June to a low fountain with a turbulent, out-pouring lava pond surrounded by a tephra cone by mid-June. During mid-June, the sound pressure level reaches a maximum, and peak frequency drops. We develop a model that uses jet noise scaling relationships to estimate changes in volcanic jet diameter and jet velocity from infrasound sound pressure levels and peak frequencies. The results of this model indicate a decrease in velocity in mid-June which coincides with the decrease in fountain height. Furthermore, the model results suggest an increase in jet diameter, which can be explained by the larger width of the fountain that resembles a turbulent lava pond compared to the distinct fountain at the beginning of June. The agreement between the infrasound-derived and visually observed changes in fountain dynamics suggests that jet noise scaling relationships can be used to monitor lava fountain dynamics using infrasound recordings.