The use of statistical point processes in geoinformation analysis

A. Stein, V. Tolpekin, Olga Spatenkova

Research output: Contribution to journalConference articleAcademicpeer-review

1 Citation (Scopus)

Abstract

Many objects in space can best be modeled statistically by using point processes. Examples are fires in an urban environment, herds of animals in large areas, earthquakes and forest fires and large speckles on a radar image. Modern developments in point process theory now much better than before allow us to make statistical models to explain the observed patterns. In this paper, we will address the way that point processes can be modeled in space and time. The first application draws from domestic fires at the city level, where we apply a statistical point pattern analysis to derive major causes from related layers of information. The second application considers earthquakes as a marked point process. For earthquakes, large and complex data sets exist including many possibly relevant covariates that may influence their occurrence. The Strauss point process model is explored to analyze earthquake data in Pakistan recorded since 1973, in particular the major earthquake event occurring in 2005. The model, despite some limitations, is rigorous for applying it to such a marked point pattern, representing well the clustering behaviour as determined by a number of environmental factors. Finally, the Strauss point process model is suggested for the use in identifying and explaining the occurrences of speckles in a radar image.

Original languageEnglish
Pages (from-to)109-113
Number of pages5
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume38
Issue numberII
Publication statusPublished - 1 Jan 2010
EventJoint International Conference on Theory, Data Handling and Modelling in GeoSpatial Information Science 2010 - Hongkong, Hong Kong
Duration: 26 May 201028 May 2010

Fingerprint

Earthquakes
natural disaster
earthquake
speckle
Fires
Speckle
radar
Radar
earthquake event
forest fire
environmental factor
Animals
Pakistan
environmental factors
analysis
animal
cause
event

Cite this

@article{cdc1199c75814fd6abc6f9e34cb0c889,
title = "The use of statistical point processes in geoinformation analysis",
abstract = "Many objects in space can best be modeled statistically by using point processes. Examples are fires in an urban environment, herds of animals in large areas, earthquakes and forest fires and large speckles on a radar image. Modern developments in point process theory now much better than before allow us to make statistical models to explain the observed patterns. In this paper, we will address the way that point processes can be modeled in space and time. The first application draws from domestic fires at the city level, where we apply a statistical point pattern analysis to derive major causes from related layers of information. The second application considers earthquakes as a marked point process. For earthquakes, large and complex data sets exist including many possibly relevant covariates that may influence their occurrence. The Strauss point process model is explored to analyze earthquake data in Pakistan recorded since 1973, in particular the major earthquake event occurring in 2005. The model, despite some limitations, is rigorous for applying it to such a marked point pattern, representing well the clustering behaviour as determined by a number of environmental factors. Finally, the Strauss point process model is suggested for the use in identifying and explaining the occurrences of speckles in a radar image.",
author = "A. Stein and V. Tolpekin and Olga Spatenkova",
year = "2010",
month = "1",
day = "1",
language = "English",
volume = "38",
pages = "109--113",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
issn = "1682-1750",
publisher = "Copernicus",
number = "II",

}

The use of statistical point processes in geoinformation analysis. / Stein, A.; Tolpekin, V.; Spatenkova, Olga.

In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 38, No. II, 01.01.2010, p. 109-113.

Research output: Contribution to journalConference articleAcademicpeer-review

TY - JOUR

T1 - The use of statistical point processes in geoinformation analysis

AU - Stein, A.

AU - Tolpekin, V.

AU - Spatenkova, Olga

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Many objects in space can best be modeled statistically by using point processes. Examples are fires in an urban environment, herds of animals in large areas, earthquakes and forest fires and large speckles on a radar image. Modern developments in point process theory now much better than before allow us to make statistical models to explain the observed patterns. In this paper, we will address the way that point processes can be modeled in space and time. The first application draws from domestic fires at the city level, where we apply a statistical point pattern analysis to derive major causes from related layers of information. The second application considers earthquakes as a marked point process. For earthquakes, large and complex data sets exist including many possibly relevant covariates that may influence their occurrence. The Strauss point process model is explored to analyze earthquake data in Pakistan recorded since 1973, in particular the major earthquake event occurring in 2005. The model, despite some limitations, is rigorous for applying it to such a marked point pattern, representing well the clustering behaviour as determined by a number of environmental factors. Finally, the Strauss point process model is suggested for the use in identifying and explaining the occurrences of speckles in a radar image.

AB - Many objects in space can best be modeled statistically by using point processes. Examples are fires in an urban environment, herds of animals in large areas, earthquakes and forest fires and large speckles on a radar image. Modern developments in point process theory now much better than before allow us to make statistical models to explain the observed patterns. In this paper, we will address the way that point processes can be modeled in space and time. The first application draws from domestic fires at the city level, where we apply a statistical point pattern analysis to derive major causes from related layers of information. The second application considers earthquakes as a marked point process. For earthquakes, large and complex data sets exist including many possibly relevant covariates that may influence their occurrence. The Strauss point process model is explored to analyze earthquake data in Pakistan recorded since 1973, in particular the major earthquake event occurring in 2005. The model, despite some limitations, is rigorous for applying it to such a marked point pattern, representing well the clustering behaviour as determined by a number of environmental factors. Finally, the Strauss point process model is suggested for the use in identifying and explaining the occurrences of speckles in a radar image.

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2010/ref/stein_use.pdf

M3 - Conference article

VL - 38

SP - 109

EP - 113

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 1682-1750

IS - II

ER -