Title: Agile Big Data Analytics of High-Volume Geodetic Data Products for Improving Science and Hazard Response
Presenting Author: Hook Hua
Organization: Jet Propulsion Laboratory / Caltech
Co-Author(s): Susan Owen, Gerald Manipon, Michael Starch, Gian Franco Sacco, Piyush Agram, Brian Bue, Anatha Ravi Kiran Lanka Subrahmanya, Sang-Ho Yun, Paul Lundgren, Angelyn Moore, Eric Fielding, Paul Rosen, Zhen Liu, Tom Farr, Frank Webb, Mark Simons, Pietro Milillo, Lan Dang, Justin Linick

Abstract:
Geodetic imaging is revolutionizing geophysics, but the scope of discovery has been limited by labor-intensive technological implementation of the analyses. The Advanced Rapid Imaging and Analysis (ARIA) project has proven capability to automate SAR data processing and analysis. Existing and upcoming SAR missions such as Sentinel-1A/B and NISAR are also expected to generate massive amounts of SAR data. This has brought to the forefront the need for analytical tools for SAR quality assessment (QA) on large volumes of SAR data, a critical step before higher level time series and velocity products can be reliably generated. Initially leveraging an advanced hybrid-cloud computing science data system for performing large-scale processing, we then applied machine learning approaches for automated analysis of various quality metrics. Machine learning-based user-training of features, cross-validation, prediction models are being integrated into our science data processing flow to enable QA analytics for enabling improvements to the production quality of geodetic data products.