Hierarchical spatial modeling and prediction of multiple soil nutrients and carbon concentrations

Anandamayee Majumdar, Jason Kaye, Corinna Gries, Diane Hope, Nancy Grimm

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Modeling the multivariate spatial distribution of soil carbon and nutrients has been a challenge for ecosystem ecologists. There is a need for explanatory models, which give insight into socio-economic and biophysical controls on soil spatial variability. We propose a hierarchical Bayesian modeling specification, an approach that takes into account the spatial covariates as well as the inter-dependent nature of soil nutrients and carbon pools. We develop the model to explain variability in soil nutrient and carbon pools in the Central Arizona Phoenix Metropolitan region where soil-composition has changed considerably over the years due to socio-economic factors. A fully Bayesian statistical analysis of how these changes have affected soil nutrients provides insight as to how socio-economics influence changes in ecology. Our model included five geomorphic, ecological, and socio-economic independent variables that were used to predict soil total N, organic C, inorganic C, and extractable [image omitted]. Using six levels of hierarchy, we fit a suitable spatial hierarhical model. Using a Bayesian co-kriging strategy, we generate appropriate values used for predictions at new locations where covariate information is unavailable. We compare prediction results from standard models and show that our model is richer and so is the interpretation. To the best of our knowledge, this is the first work that applies hierarchical Bayesian modeling techniques and kriging strategies to study multivarate soil nutrient and carbon concentrations. We conclude a discussion of our findings and the broader ecological applicability of our modeling style.

Original languageEnglish (US)
Pages (from-to)434-453
Number of pages20
JournalCommunications in Statistics: Simulation and Computation
Volume37
Issue number2
DOIs
StatePublished - Feb 2008

Fingerprint

Spatial Prediction
Spatial Modeling
Hierarchical Modeling
Nutrients
Soil
Carbon
Soils
Economics
Bayesian Modeling
Covariates
Cokriging
Spatial Variability
Prediction
Kriging
Spatial Model
Multivariate Distribution
Ecology
Bayesian Analysis
Ecosystem
Spatial Distribution

Keywords

  • Bayesian framework
  • Coregionalization
  • Gibbs sampling
  • Hierarchical modeling
  • Markov chain Monte Carlo
  • Multivariate spatial processes

ASJC Scopus subject areas

  • Modeling and Simulation
  • Statistics and Probability

Cite this

Hierarchical spatial modeling and prediction of multiple soil nutrients and carbon concentrations. / Majumdar, Anandamayee; Kaye, Jason; Gries, Corinna; Hope, Diane; Grimm, Nancy.

In: Communications in Statistics: Simulation and Computation, Vol. 37, No. 2, 02.2008, p. 434-453.

Research output: Contribution to journalArticle

Majumdar, Anandamayee ; Kaye, Jason ; Gries, Corinna ; Hope, Diane ; Grimm, Nancy. / Hierarchical spatial modeling and prediction of multiple soil nutrients and carbon concentrations. In: Communications in Statistics: Simulation and Computation. 2008 ; Vol. 37, No. 2. pp. 434-453.
@article{8c8746c89d174f7b8761d81f0e714e7e,
title = "Hierarchical spatial modeling and prediction of multiple soil nutrients and carbon concentrations",
abstract = "Modeling the multivariate spatial distribution of soil carbon and nutrients has been a challenge for ecosystem ecologists. There is a need for explanatory models, which give insight into socio-economic and biophysical controls on soil spatial variability. We propose a hierarchical Bayesian modeling specification, an approach that takes into account the spatial covariates as well as the inter-dependent nature of soil nutrients and carbon pools. We develop the model to explain variability in soil nutrient and carbon pools in the Central Arizona Phoenix Metropolitan region where soil-composition has changed considerably over the years due to socio-economic factors. A fully Bayesian statistical analysis of how these changes have affected soil nutrients provides insight as to how socio-economics influence changes in ecology. Our model included five geomorphic, ecological, and socio-economic independent variables that were used to predict soil total N, organic C, inorganic C, and extractable [image omitted]. Using six levels of hierarchy, we fit a suitable spatial hierarhical model. Using a Bayesian co-kriging strategy, we generate appropriate values used for predictions at new locations where covariate information is unavailable. We compare prediction results from standard models and show that our model is richer and so is the interpretation. To the best of our knowledge, this is the first work that applies hierarchical Bayesian modeling techniques and kriging strategies to study multivarate soil nutrient and carbon concentrations. We conclude a discussion of our findings and the broader ecological applicability of our modeling style.",
keywords = "Bayesian framework, Coregionalization, Gibbs sampling, Hierarchical modeling, Markov chain Monte Carlo, Multivariate spatial processes",
author = "Anandamayee Majumdar and Jason Kaye and Corinna Gries and Diane Hope and Nancy Grimm",
year = "2008",
month = "2",
doi = "10.1080/03610910701792588",
language = "English (US)",
volume = "37",
pages = "434--453",
journal = "Communications in Statistics: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Hierarchical spatial modeling and prediction of multiple soil nutrients and carbon concentrations

AU - Majumdar, Anandamayee

AU - Kaye, Jason

AU - Gries, Corinna

AU - Hope, Diane

AU - Grimm, Nancy

PY - 2008/2

Y1 - 2008/2

N2 - Modeling the multivariate spatial distribution of soil carbon and nutrients has been a challenge for ecosystem ecologists. There is a need for explanatory models, which give insight into socio-economic and biophysical controls on soil spatial variability. We propose a hierarchical Bayesian modeling specification, an approach that takes into account the spatial covariates as well as the inter-dependent nature of soil nutrients and carbon pools. We develop the model to explain variability in soil nutrient and carbon pools in the Central Arizona Phoenix Metropolitan region where soil-composition has changed considerably over the years due to socio-economic factors. A fully Bayesian statistical analysis of how these changes have affected soil nutrients provides insight as to how socio-economics influence changes in ecology. Our model included five geomorphic, ecological, and socio-economic independent variables that were used to predict soil total N, organic C, inorganic C, and extractable [image omitted]. Using six levels of hierarchy, we fit a suitable spatial hierarhical model. Using a Bayesian co-kriging strategy, we generate appropriate values used for predictions at new locations where covariate information is unavailable. We compare prediction results from standard models and show that our model is richer and so is the interpretation. To the best of our knowledge, this is the first work that applies hierarchical Bayesian modeling techniques and kriging strategies to study multivarate soil nutrient and carbon concentrations. We conclude a discussion of our findings and the broader ecological applicability of our modeling style.

AB - Modeling the multivariate spatial distribution of soil carbon and nutrients has been a challenge for ecosystem ecologists. There is a need for explanatory models, which give insight into socio-economic and biophysical controls on soil spatial variability. We propose a hierarchical Bayesian modeling specification, an approach that takes into account the spatial covariates as well as the inter-dependent nature of soil nutrients and carbon pools. We develop the model to explain variability in soil nutrient and carbon pools in the Central Arizona Phoenix Metropolitan region where soil-composition has changed considerably over the years due to socio-economic factors. A fully Bayesian statistical analysis of how these changes have affected soil nutrients provides insight as to how socio-economics influence changes in ecology. Our model included five geomorphic, ecological, and socio-economic independent variables that were used to predict soil total N, organic C, inorganic C, and extractable [image omitted]. Using six levels of hierarchy, we fit a suitable spatial hierarhical model. Using a Bayesian co-kriging strategy, we generate appropriate values used for predictions at new locations where covariate information is unavailable. We compare prediction results from standard models and show that our model is richer and so is the interpretation. To the best of our knowledge, this is the first work that applies hierarchical Bayesian modeling techniques and kriging strategies to study multivarate soil nutrient and carbon concentrations. We conclude a discussion of our findings and the broader ecological applicability of our modeling style.

KW - Bayesian framework

KW - Coregionalization

KW - Gibbs sampling

KW - Hierarchical modeling

KW - Markov chain Monte Carlo

KW - Multivariate spatial processes

UR - http://www.scopus.com/inward/record.url?scp=38949165146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38949165146&partnerID=8YFLogxK

U2 - 10.1080/03610910701792588

DO - 10.1080/03610910701792588

M3 - Article

AN - SCOPUS:38949165146

VL - 37

SP - 434

EP - 453

JO - Communications in Statistics: Simulation and Computation

JF - Communications in Statistics: Simulation and Computation

SN - 0361-0918

IS - 2

ER -