Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing

Bas Van De Kerkhof, Victor Pankratius, Ling Chang, Rob Van Swol, Ramon F. Hanssen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

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.

Original languageEnglish
Title of host publication2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
Place of PublicationValencia
PublisherIEEE
Pages4427-4430
Number of pages4
ISBN (Electronic)9781538671504
DOIs
Publication statusPublished - 31 Oct 2018
Externally publishedYes
Event38th IEEE International Geoscience and Remote Sensing Symposium 2018: Observing, Understanding and Forcasting the Dynamics of Our Planet - Feria Valencia Convention & Exhibition Center, Valencia, Spain
Duration: 22 Jul 201827 Jul 2018
Conference number: 38
https://www.igarss2018.org/

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2018-July

Conference

Conference38th IEEE International Geoscience and Remote Sensing Symposium 2018
Abbreviated titleIGARSS 2018
CountrySpain
CityValencia
Period22/07/1827/07/18
Internet address

Fingerprint

hypothesis testing
Parameterization
Learning systems
parameterization
Time series
Testing
modeling
time series
Processing
Learning algorithms
temporal analysis
testing method
data interpretation
Semantics
spatial analysis
machine learning
method

Keywords

  • Hypothesis testing
  • InSAR
  • Machine learning
  • Stochastics

Cite this

Van De Kerkhof, B., Pankratius, V., Chang, L., Van Swol, R., & Hanssen, R. F. (2018). Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings (pp. 4427-4430). [8518460] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018-July). Valencia: IEEE. https://doi.org/10.1109/IGARSS.2018.8518460
Van De Kerkhof, Bas ; Pankratius, Victor ; Chang, Ling ; Van Swol, Rob ; Hanssen, Ramon F. / Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing. 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Valencia : IEEE, 2018. pp. 4427-4430 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{b10da3e47e7a41e395d2a4a787f25846,
title = "Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing",
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.",
keywords = "Hypothesis testing, InSAR, Machine learning, Stochastics",
author = "{Van De Kerkhof}, Bas and Victor Pankratius and Ling Chang and {Van Swol}, Rob and Hanssen, {Ramon F.}",
year = "2018",
month = "10",
day = "31",
doi = "10.1109/IGARSS.2018.8518460",
language = "English",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "IEEE",
pages = "4427--4430",
booktitle = "2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings",
address = "United States",

}

Van De Kerkhof, B, Pankratius, V, Chang, L, Van Swol, R & Hanssen, RF 2018, Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing. in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings., 8518460, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2018-July, IEEE, Valencia, pp. 4427-4430, 38th IEEE International Geoscience and Remote Sensing Symposium 2018, Valencia, Spain, 22/07/18. https://doi.org/10.1109/IGARSS.2018.8518460

Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing. / Van De Kerkhof, Bas; Pankratius, Victor; Chang, Ling; Van Swol, Rob; Hanssen, Ramon F.

2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Valencia : IEEE, 2018. p. 4427-4430 8518460 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2018-July).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing

AU - Van De Kerkhof, Bas

AU - Pankratius, Victor

AU - Chang, Ling

AU - Van Swol, Rob

AU - Hanssen, Ramon F.

PY - 2018/10/31

Y1 - 2018/10/31

N2 - 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.

AB - 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.

KW - Hypothesis testing

KW - InSAR

KW - Machine learning

KW - Stochastics

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1109/IGARSS.2018.8518460

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2018/chap/chang_aut.pdf

U2 - 10.1109/IGARSS.2018.8518460

DO - 10.1109/IGARSS.2018.8518460

M3 - Conference contribution

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4427

EP - 4430

BT - 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings

PB - IEEE

CY - Valencia

ER -

Van De Kerkhof B, Pankratius V, Chang L, Van Swol R, Hanssen RF. Automatic InSAR phase modeling and quality assessment using machine learning and hypothesis testing. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Valencia: IEEE. 2018. p. 4427-4430. 8518460. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2018.8518460