Automatic Insar Phase Modeling and Quality Assessment Using Machine Learning and Hypothesis Testing

Conference Paper (2018)
Author(s)

B. van de Kerkhof (TU Delft - Mathematical Geodesy and Positioning, Massachusetts Institute of Technology, Royal Netherlands Aerospace Centre NLR)

Victor Pankratius (Massachusetts Institute of Technology)

L. Chang (TU Delft - Mathematical Geodesy and Positioning)

Rob Van Swol (Royal Netherlands Aerospace Centre NLR)

Ramon Hanssen (TU Delft - Mathematical Geodesy and Positioning)

Research Group
Mathematical Geodesy and Positioning
DOI related publication
https://doi.org/10.1109/IGARSS.2018.8518460
More Info
expand_more
Publication Year
2018
Language
English
Research Group
Mathematical Geodesy and Positioning
Volume number
2018
Pages (from-to)
4427-4430
ISBN (print)
978-1-5386-7151-1
ISBN (electronic)
978-1-5386-7150-4

Abstract

PS-InSAR time series yield large volumes of data points, observed during many epochs. While traditional processing algorithms use a single parameterization for the behavior of all points, in reality this behavior will differ significantly between points and over time. It is a challenge to find the optimal parameterization for this behavior, and to assess the quality of the measurements per point and per epoch. Here we propose a post-processing method to improve the model estimation of PS-InSAR phase time series. The method combines machine learning (ML) algorithms and hypothesis testing (HT) into the ML/HT method efficiently leading to significant improvements in data interpretation, parameterization, as well as the quality of the estimated parameters. Moreover we show that we can find structure in the data regardless of spatial location and temporal complexity. In contrast to conventional assumptions that nearby points behave in the same way, with unchanged characteristics over time, a method is developed that takes individual behavior into account. Demonstrating that we can move from spatial and temporal analysis tools to semantic-based analysis.

No files available

Metadata only record. There are no files for this record.