English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Satellites enable widespread, regional or global surveillance of volcanoesand can provide the first indication of volcanic unrest or eruption. Here weconsider Interferometric Synthetic Aperture Radar (InSAR), which can beemployed to detect surface deformation with a strong statistical link toeruption. The ability of machine learning to automatically identify signals ofinterest in these large InSAR datasets has already been demonstrated, butdata-driven techniques, such as convolutional neutral networks (CNN) requirebalanced training datasets of positive and negative signals to effectivelydifferentiate between real deformation and noise. As only a small proportion ofvolcanoes are deforming and atmospheric noise is ubiquitous, the use of machinelearning for detecting volcanic unrest is more challenging. In this paper, weaddress this problem using synthetic interferograms to train the AlexNet. Thesynthetic interferograms are composed of 3 parts: 1) deformation patterns basedon a Monte Carlo selection of parameters for analytic forward models, 2)stratified atmospheric effects derived from weather models and 3) turbulentatmospheric effects based on statistical simulations of correlated noise. TheAlexNet architecture trained with synthetic data outperforms that trained usingreal interferograms alone, based on classification accuracy and positivepredictive value (PPV). However, the models used to generate the syntheticsignals are a simplification of the natural processes, so we retrain the CNNwith a combined dataset consisting of synthetic models and selected realexamples, achieving a final PPV of 82%. Although applying atmosphericcorrections to the entire dataset is computationally expensive, it isrelatively simple to apply them to the small subset of positive results. Thisfurther improves the detection performance without a significant increase incomputational burden.

A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets