TY - JOUR
T1 - Automatic Detection of Volcanic Surface Deformation Using Deep Learning
AU - Sun, Jian
AU - Wauthier, Christelle
AU - Stephens, Kirsten
AU - Gervais, Melissa
AU - Cervone, Guido
AU - La Femina, Peter
AU - Higgins, Machel
N1 - Funding Information:
This study was funded by National Aeronautics and Space Administration (NASA) Earth Surface and Interior (ESI) Grant NNX17AD70G to P.C.L. and C.W. and Grants ESI NNX16AK87G and ESI 80NSSC20K0490 to C.W., NSF Grant EAR‐0911546 to P.C.L., and the Penn State College of Earth and Mineral Sciences “Postdoc‐Facilitated Innovation through Collaboration” award to J.S.
Funding Information:
This study was funded by National Aeronautics and Space Administration (NASA) Earth Surface and Interior (ESI) Grant NNX17AD70G to P.C.L. and C.W. and Grants ESI NNX16AK87G and ESI 80NSSC20K0490 to C.W., NSF Grant EAR-0911546 to P.C.L., and the Penn State College of Earth and Mineral Sciences ?Postdoc-Facilitated Innovation through Collaboration? award to J.S.
Publisher Copyright:
© 2020. American Geophysical Union. All Rights Reserved.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Interferometric Synthetic Aperture Radar (InSAR) provides subcentimetric measurements of surface displacements, which are key for characterizing and monitoring magmatic processes in volcanic regions. The abundant measurements of surface displacements in multitemporal InSAR data routinely acquired by SAR satellites can facilitate near real-time volcano monitoring on a global basis. However, the presence of atmospheric signals in interferograms complicates the interpretation of those InSAR measurements, which can even lead to a misinterpretation of InSAR signals and volcanic unrest. Given the vast quantities of SAR data available, an automatic InSAR data processing and denoising approach is required to separate volcanic signals that are cause of concern from atmospheric signals and noise. In this study, we employ a deep learning strategy that directly removes atmospheric and other noise signals from time-consecutive unwrapped surface displacements obtained through an InSAR time series approach using an end-to-end convolutional neural network (CNN) with an encoder-decoder architecture, modified U-net. The CNN is trained with simulated synthetic unwrapped surface displacement maps and is then applied to real InSAR data. Our proposed architecture is capable of detecting dynamic spatio-temporal patterns of volcanic surface displacements. We find that an ensemble-average strategy is recommended to stabilize detected results for varying deformation rates and signal-to-noise ratios (SNRs). A case study is also presented where this method is applied to InSAR data covering Masaya volcano, Nicaragua and the results are validated using continuous GPS data. The results confirm that our network can indeed efficiently suppress atmospheric and other noise to reveal the noise-free surface deformation.
AB - Interferometric Synthetic Aperture Radar (InSAR) provides subcentimetric measurements of surface displacements, which are key for characterizing and monitoring magmatic processes in volcanic regions. The abundant measurements of surface displacements in multitemporal InSAR data routinely acquired by SAR satellites can facilitate near real-time volcano monitoring on a global basis. However, the presence of atmospheric signals in interferograms complicates the interpretation of those InSAR measurements, which can even lead to a misinterpretation of InSAR signals and volcanic unrest. Given the vast quantities of SAR data available, an automatic InSAR data processing and denoising approach is required to separate volcanic signals that are cause of concern from atmospheric signals and noise. In this study, we employ a deep learning strategy that directly removes atmospheric and other noise signals from time-consecutive unwrapped surface displacements obtained through an InSAR time series approach using an end-to-end convolutional neural network (CNN) with an encoder-decoder architecture, modified U-net. The CNN is trained with simulated synthetic unwrapped surface displacement maps and is then applied to real InSAR data. Our proposed architecture is capable of detecting dynamic spatio-temporal patterns of volcanic surface displacements. We find that an ensemble-average strategy is recommended to stabilize detected results for varying deformation rates and signal-to-noise ratios (SNRs). A case study is also presented where this method is applied to InSAR data covering Masaya volcano, Nicaragua and the results are validated using continuous GPS data. The results confirm that our network can indeed efficiently suppress atmospheric and other noise to reveal the noise-free surface deformation.
UR - http://www.scopus.com/inward/record.url?scp=85091479777&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091479777&partnerID=8YFLogxK
U2 - 10.1029/2020JB019840
DO - 10.1029/2020JB019840
M3 - Article
AN - SCOPUS:85091479777
SN - 2169-9313
VL - 125
JO - Journal of Geophysical Research: Solid Earth
JF - Journal of Geophysical Research: Solid Earth
IS - 9
M1 - e2020JB019840
ER -