nerc.ac.uk

Automated Insar Time-Series Analysis Tool for Geological Interpretations in Near-Real Time

Hourston, Holly; Gonzalez Alvarez, Itahisa; Bateson, Luke; Hussain, Ekbal; Novellino, Alessandro. 2024 Automated Insar Time-Series Analysis Tool for Geological Interpretations in Near-Real Time. In: IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 7-12 July 2024. IEEE, 9971-9974.

Before downloading, please read NORA policies.
[thumbnail of IGARSS_HHourston_2024_submission_final.pdf]
Preview
Text
IGARSS_HHourston_2024_submission_final.pdf - Accepted Version
Available under License Creative Commons Attribution 4.0.

Download (478kB) | Preview

Abstract/Summary

Large EO datasets are becoming increasingly challenging to analyse and interpret due to their size, a problem that will continue to worsen with longer satellite operating times. In this manuscript, we present an automatic tool to analyse interferometric synthetic aperture radar (InSAR)-derived deformation time series using a supervised machine learning regression algorithm. This processing tool at its current stage of development can map areas of anomalous ground motions, and different extents of seasonal behaviours. With the addition of British Geological Survey proprietary geological hazard susceptibility datasets, we can begin to make further interpretations of the ground movements. This algorithm will aid in the task of identifying areas of substantial long-term ground motions due to specific geological hazards. This will be applied specifically to vulnerable locations such as coastlines, and will be used to identify locations at risk of exacerbated seasonal ground motions due to the worsening effects of climate change.

Item Type: Publication - Conference Item (Paper)
Digital Object Identifier (DOI): 10.1109/IGARSS53475.2024.10641304
ISBN: 979-8-3503-6032-5
Date made live: 27 Jun 2025 14:02 +0 (UTC)
URI: https://nora.nerc.ac.uk/id/eprint/539712

Actions (login required)

View Item View Item

Document Downloads

Downloads for past 30 days

Downloads per month over past year

More statistics for this item...