Skip to main content
The search returned 3 results
Now showing 1 - 3 of 3
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Open Access ,

    Detection of Subtle Thermal Anomalies: Deep Learning Applied to the ASTER Global Volcano Dataset

    Twenty-one years of ASTER global thermal infrared (TIR) acquisitions provide a large amount of data for volcano monitoring. These data, with high spatial and spectral resolution, enable routine investigations of volcanoes in remote and inaccessible regions, including those with no ground-based monitoring. However, the dataset is too large to be manually analyzed on a global basis. Here, we systematically process the data over several volcanoes using a deep learning algorithm to automatically extract volcanic thermal anomalies. We explore the application of a Convolutional Neural Network (CNN), specifically UNET, to detect subtle to intense anomalies exploiting the spatial relationships of the volcanic features. We employ a supervised UNET network trained with the largest (1500) labeled dataset of ASTER TIR images from five different volcanoes, namely Etna (Italy), Popocatépetl (Mexico), Lascar (Chile), Fuego (Guatemala), and Kliuchevskoi (Russia). We show that our approach achieves high accuracy (93%) with excellent generalization capabilities. The effectiveness of our model for detecting the full range of thermal emission is shown for volcanoes with very different styles of activity and tested at Vulcano (Italy). The results demonstrate the potential applicability of the proposed approach to the development of automated thermal analysis systems at the global scale using future TIR data such as the planned NASA SBG mission.
      67  119
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Open Access ,

    Statistical retrieval of volcanic activity in long time series orbital data: Implications for forecasting future activity

    Several high spatial resolution thermal infrared (TIR) missions are planned for the coming decade and their data will be crucial to constrain volcanic activity patterns throughout pre- and post-eruption phases. Foundational to these patterns is the subtle (1−2 K) thermal behavior, which is easily overlooked using lower spatial resolution data. In preparation for these new data, we conducted the first study using the entire twenty-two-year archive of higher spatial, lower temporal resolution TIR data from the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) sensor. This archive presents a unique opportunity to quantify low-magnitude temperature anomalies and small plumes over long time periods. We developed a new statistical algorithm to automatically detect the full range of thermal activity and applied it to >5000 ASTER scenes of five volcanoes with well-documented eruptions. Unique to this algorithm is its ability to use both day and night data, account for clouds, quantify accurate background temperatures, and dynamically scale depending on the anomaly size. Results improve upon those from the more commonly used lower spatial resolution data, despite the less frequent temporal coverage of ASTER, and show that high spatial resolution TIR data are equally as effective. Significantly, the smaller, subtle thermal detections served as precursory signals in ∼81% of eruptions, and the algorithm's results create a framework for classifying future eruptive styles.
      47  51
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Restricted ,

    The protracted development of focused magmatic intrusion during continental rifting

    The transition from mechanical thinning toward focused magmatic intrusion during continental rifting is poorly constrained; the tectonically active Main Ethiopian Rift (MER) provides an ideal study locale to address this issue. The presence of linear magmatic-tectonic belts in the relatively immature central MER may indicate that the transition from mechanical to magmatic rifting is more spatially distributed and temporally protracted than has previously been assumed. Here we examine lava geochemistry and vent distribution of a Pliocene-Quaternary linear magmatic chain along the western margin of the central MER—the Akaki Magmatic Zone. Our results show limited variability in parental magma that evolve in a complex polybaric fractionation system that has not changed significantly over the past 3 Ma. Our results suggest the following: (1) channeling of plume material and the localization of shear- or topography-induced porosity modulates melt intrusion into the continental lithosphere. (2) Pre-existing lithospheric structures may act as catalysts for intrusion of magmas into the lithospheric mantle. (3) The midcrustal to upper crustal strain regime dictates the surface orientation of volcanic vents. Therefore, although linear magmatic belts like those in the central MER may young progressively toward the rift axis and superficially resemble oceanic style magmatism, they actually represent prebreakup magmatism on continental crust. The oldest linear magmatic belts observed seismically and magnetically at the edge of the ocean basins thus may not, as is often assumed, actually mark the onset of seafloor spreading.
      162  24