Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets

Suniti Karunatillake, Olivier Gasnault, Steven W. Squyres, John M. Keller, Daniel M. Janes, William V. Boynton, Horton E. Newsom

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

We synthesize multivariate correlation and regression methods to characterize unique relationships among compositional and physical properties of a planetary surface locally, regionally, and globally. Martian data including elemental mass fractions, areal fractions of mineral types, and thermal inertia constitute our case study. We incorporate techniques to address the effects of spatial autocorrelation and heteroscedasticity. We also utilize method and fit diagnostics. While the Mars Odyssey and Mars Global Surveyor missions provide the exploratory context in our discussion, our approach is applicable whenever the interrelationships of spatially binned data of continuous-valued planetary attributes are sought. For example, our regional-scale case study reinforces the strength of the spatial correlation among K, Th, and the dominant mineralogic type within northern low albedo regions (surface type 2) of Mars. Recent chemical and mineralogic data from the MESSENGER mission at Mercury and Dawn at Vesta may be analyzed effectively with these hierarchical regression methods to constrain geochemical processes. Likewise, our algorithm could be applied locally with the wide variety of compositional data expected from the MSL mission at Gale Crater in general, and the ChemCam sampling grids in particular.

Original languageEnglish (US)
Pages (from-to)253-273
Number of pages21
JournalEarth, Moon and Planets
Volume108
Issue number3-4
DOIs
StatePublished - Jun 2012

Fingerprint

regression analysis
Mars
mars
MESSENGER (spacecraft)
planetary surfaces
Mars Global Surveyor
albedo
craters
inertia
planetary surface
autocorrelation
physical properties
sampling
grids
minerals
crater
physical property
mineral
method

Keywords

  • Analysis of variance
  • Curiosity rover
  • Dawn vesta
  • Diagnosticstatistics
  • Geochemistry
  • Geographic information system
  • GIS
  • Heteroscedasticity
  • Hierarchical correlation
  • Hierarchical regression
  • Mars global surveyor
  • Mars Odyssey
  • Mars Odyssey GRS
  • Mars science laboratory
  • MESSENGER
  • MGS
  • Multivariate correlation
  • Multivariate regression
  • Planetary data
  • Planetary data analysis
  • Scatterplot software
  • Spatial autocorrelation
  • Spatial data
  • Statistics for spatial data
  • Surface type 2

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)
  • Astronomy and Astrophysics
  • Space and Planetary Science

Cite this

Karunatillake, S., Gasnault, O., Squyres, S. W., Keller, J. M., Janes, D. M., Boynton, W. V., & Newsom, H. E. (2012). Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets. Earth, Moon and Planets, 108(3-4), 253-273. https://doi.org/10.1007/s11038-012-9395-x

Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets. / Karunatillake, Suniti; Gasnault, Olivier; Squyres, Steven W.; Keller, John M.; Janes, Daniel M.; Boynton, William V.; Newsom, Horton E.

In: Earth, Moon and Planets, Vol. 108, No. 3-4, 06.2012, p. 253-273.

Research output: Contribution to journalArticle

Karunatillake, S, Gasnault, O, Squyres, SW, Keller, JM, Janes, DM, Boynton, WV & Newsom, HE 2012, 'Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets', Earth, Moon and Planets, vol. 108, no. 3-4, pp. 253-273. https://doi.org/10.1007/s11038-012-9395-x
Karunatillake, Suniti ; Gasnault, Olivier ; Squyres, Steven W. ; Keller, John M. ; Janes, Daniel M. ; Boynton, William V. ; Newsom, Horton E. / Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets. In: Earth, Moon and Planets. 2012 ; Vol. 108, No. 3-4. pp. 253-273.
@article{f8c6db4e872c4c2f8eba1835b8724951,
title = "Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets",
abstract = "We synthesize multivariate correlation and regression methods to characterize unique relationships among compositional and physical properties of a planetary surface locally, regionally, and globally. Martian data including elemental mass fractions, areal fractions of mineral types, and thermal inertia constitute our case study. We incorporate techniques to address the effects of spatial autocorrelation and heteroscedasticity. We also utilize method and fit diagnostics. While the Mars Odyssey and Mars Global Surveyor missions provide the exploratory context in our discussion, our approach is applicable whenever the interrelationships of spatially binned data of continuous-valued planetary attributes are sought. For example, our regional-scale case study reinforces the strength of the spatial correlation among K, Th, and the dominant mineralogic type within northern low albedo regions (surface type 2) of Mars. Recent chemical and mineralogic data from the MESSENGER mission at Mercury and Dawn at Vesta may be analyzed effectively with these hierarchical regression methods to constrain geochemical processes. Likewise, our algorithm could be applied locally with the wide variety of compositional data expected from the MSL mission at Gale Crater in general, and the ChemCam sampling grids in particular.",
keywords = "Analysis of variance, Curiosity rover, Dawn vesta, Diagnosticstatistics, Geochemistry, Geographic information system, GIS, Heteroscedasticity, Hierarchical correlation, Hierarchical regression, Mars global surveyor, Mars Odyssey, Mars Odyssey GRS, Mars science laboratory, MESSENGER, MGS, Multivariate correlation, Multivariate regression, Planetary data, Planetary data analysis, Scatterplot software, Spatial autocorrelation, Spatial data, Statistics for spatial data, Surface type 2",
author = "Suniti Karunatillake and Olivier Gasnault and Squyres, {Steven W.} and Keller, {John M.} and Janes, {Daniel M.} and Boynton, {William V.} and Newsom, {Horton E.}",
year = "2012",
month = "6",
doi = "10.1007/s11038-012-9395-x",
language = "English (US)",
volume = "108",
pages = "253--273",
journal = "Earth, Moon and Planets",
issn = "0167-9295",
publisher = "Springer Netherlands",
number = "3-4",

}

TY - JOUR

T1 - Martian Case Study of Multivariate Correlation and Regression with Planetary Datasets

AU - Karunatillake, Suniti

AU - Gasnault, Olivier

AU - Squyres, Steven W.

AU - Keller, John M.

AU - Janes, Daniel M.

AU - Boynton, William V.

AU - Newsom, Horton E.

PY - 2012/6

Y1 - 2012/6

N2 - We synthesize multivariate correlation and regression methods to characterize unique relationships among compositional and physical properties of a planetary surface locally, regionally, and globally. Martian data including elemental mass fractions, areal fractions of mineral types, and thermal inertia constitute our case study. We incorporate techniques to address the effects of spatial autocorrelation and heteroscedasticity. We also utilize method and fit diagnostics. While the Mars Odyssey and Mars Global Surveyor missions provide the exploratory context in our discussion, our approach is applicable whenever the interrelationships of spatially binned data of continuous-valued planetary attributes are sought. For example, our regional-scale case study reinforces the strength of the spatial correlation among K, Th, and the dominant mineralogic type within northern low albedo regions (surface type 2) of Mars. Recent chemical and mineralogic data from the MESSENGER mission at Mercury and Dawn at Vesta may be analyzed effectively with these hierarchical regression methods to constrain geochemical processes. Likewise, our algorithm could be applied locally with the wide variety of compositional data expected from the MSL mission at Gale Crater in general, and the ChemCam sampling grids in particular.

AB - We synthesize multivariate correlation and regression methods to characterize unique relationships among compositional and physical properties of a planetary surface locally, regionally, and globally. Martian data including elemental mass fractions, areal fractions of mineral types, and thermal inertia constitute our case study. We incorporate techniques to address the effects of spatial autocorrelation and heteroscedasticity. We also utilize method and fit diagnostics. While the Mars Odyssey and Mars Global Surveyor missions provide the exploratory context in our discussion, our approach is applicable whenever the interrelationships of spatially binned data of continuous-valued planetary attributes are sought. For example, our regional-scale case study reinforces the strength of the spatial correlation among K, Th, and the dominant mineralogic type within northern low albedo regions (surface type 2) of Mars. Recent chemical and mineralogic data from the MESSENGER mission at Mercury and Dawn at Vesta may be analyzed effectively with these hierarchical regression methods to constrain geochemical processes. Likewise, our algorithm could be applied locally with the wide variety of compositional data expected from the MSL mission at Gale Crater in general, and the ChemCam sampling grids in particular.

KW - Analysis of variance

KW - Curiosity rover

KW - Dawn vesta

KW - Diagnosticstatistics

KW - Geochemistry

KW - Geographic information system

KW - GIS

KW - Heteroscedasticity

KW - Hierarchical correlation

KW - Hierarchical regression

KW - Mars global surveyor

KW - Mars Odyssey

KW - Mars Odyssey GRS

KW - Mars science laboratory

KW - MESSENGER

KW - MGS

KW - Multivariate correlation

KW - Multivariate regression

KW - Planetary data

KW - Planetary data analysis

KW - Scatterplot software

KW - Spatial autocorrelation

KW - Spatial data

KW - Statistics for spatial data

KW - Surface type 2

UR - http://www.scopus.com/inward/record.url?scp=84863539367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863539367&partnerID=8YFLogxK

U2 - 10.1007/s11038-012-9395-x

DO - 10.1007/s11038-012-9395-x

M3 - Article

AN - SCOPUS:84863539367

VL - 108

SP - 253

EP - 273

JO - Earth, Moon and Planets

JF - Earth, Moon and Planets

SN - 0167-9295

IS - 3-4

ER -