Regression tools for CO2 inversions

Application of a shrinkage estimator to process attribution

Benjamin Adam Shaby, Christopher B. Field

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this study we perform an atmospheric inversion based on a shrinkage estimator. This method is used to estimate surface fluxes of CO2, first partitioned according to constituent geographic regions, and then according to constituent processes that are responsible for the total flux. Our approach differs from previous approaches in two important ways. The first is that the technique of linear Bayesian inversion is recast as a regression problem. Seen as such, standard regression tools are employed to analyse and reduce errors in the resultant estimates. A shrinkage estimator, which combines standard ridge regression with the linear 'Bayesian inversion' model, is introduced. This method introduces additional bias into the model with the aim of reducing variance such that errors are decreased overall. Compared with standard linear Bayesian inversion, the ridge technique seems to reduce both flux estimation errors and prediction errors. The second divergence from previous studies is that instead of dividing the world into geographically distinct regions and estimating the CO2 flux in each region, the flux space is divided conceptually into processes that contribute to the total global flux. Formulating the problem in this manner adds to the interpretability of the resultant estimates and attempts to shed light on the problem of attributing sources and sinks to their underlying mechanisms.

Original languageEnglish (US)
Pages (from-to)279-292
Number of pages14
JournalTellus, Series B: Chemical and Physical Meteorology
Volume58
Issue number4
DOIs
StatePublished - Sep 1 2006

Fingerprint

surface flux
divergence
prediction
inversion
method
atmospheric inversion
world

All Science Journal Classification (ASJC) codes

  • Atmospheric Science

Cite this

@article{2ac734bcf738402583c3bd6f48e783dc,
title = "Regression tools for CO2 inversions: Application of a shrinkage estimator to process attribution",
abstract = "In this study we perform an atmospheric inversion based on a shrinkage estimator. This method is used to estimate surface fluxes of CO2, first partitioned according to constituent geographic regions, and then according to constituent processes that are responsible for the total flux. Our approach differs from previous approaches in two important ways. The first is that the technique of linear Bayesian inversion is recast as a regression problem. Seen as such, standard regression tools are employed to analyse and reduce errors in the resultant estimates. A shrinkage estimator, which combines standard ridge regression with the linear 'Bayesian inversion' model, is introduced. This method introduces additional bias into the model with the aim of reducing variance such that errors are decreased overall. Compared with standard linear Bayesian inversion, the ridge technique seems to reduce both flux estimation errors and prediction errors. The second divergence from previous studies is that instead of dividing the world into geographically distinct regions and estimating the CO2 flux in each region, the flux space is divided conceptually into processes that contribute to the total global flux. Formulating the problem in this manner adds to the interpretability of the resultant estimates and attempts to shed light on the problem of attributing sources and sinks to their underlying mechanisms.",
author = "Shaby, {Benjamin Adam} and Field, {Christopher B.}",
year = "2006",
month = "9",
day = "1",
doi = "10.1111/j.1600-0889.2006.00189.x",
language = "English (US)",
volume = "58",
pages = "279--292",
journal = "Tellus, Series B: Chemical and Physical Meteorology",
issn = "0280-6509",
publisher = "Co-Action Publishing",
number = "4",

}

Regression tools for CO2 inversions : Application of a shrinkage estimator to process attribution. / Shaby, Benjamin Adam; Field, Christopher B.

In: Tellus, Series B: Chemical and Physical Meteorology, Vol. 58, No. 4, 01.09.2006, p. 279-292.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Regression tools for CO2 inversions

T2 - Application of a shrinkage estimator to process attribution

AU - Shaby, Benjamin Adam

AU - Field, Christopher B.

PY - 2006/9/1

Y1 - 2006/9/1

N2 - In this study we perform an atmospheric inversion based on a shrinkage estimator. This method is used to estimate surface fluxes of CO2, first partitioned according to constituent geographic regions, and then according to constituent processes that are responsible for the total flux. Our approach differs from previous approaches in two important ways. The first is that the technique of linear Bayesian inversion is recast as a regression problem. Seen as such, standard regression tools are employed to analyse and reduce errors in the resultant estimates. A shrinkage estimator, which combines standard ridge regression with the linear 'Bayesian inversion' model, is introduced. This method introduces additional bias into the model with the aim of reducing variance such that errors are decreased overall. Compared with standard linear Bayesian inversion, the ridge technique seems to reduce both flux estimation errors and prediction errors. The second divergence from previous studies is that instead of dividing the world into geographically distinct regions and estimating the CO2 flux in each region, the flux space is divided conceptually into processes that contribute to the total global flux. Formulating the problem in this manner adds to the interpretability of the resultant estimates and attempts to shed light on the problem of attributing sources and sinks to their underlying mechanisms.

AB - In this study we perform an atmospheric inversion based on a shrinkage estimator. This method is used to estimate surface fluxes of CO2, first partitioned according to constituent geographic regions, and then according to constituent processes that are responsible for the total flux. Our approach differs from previous approaches in two important ways. The first is that the technique of linear Bayesian inversion is recast as a regression problem. Seen as such, standard regression tools are employed to analyse and reduce errors in the resultant estimates. A shrinkage estimator, which combines standard ridge regression with the linear 'Bayesian inversion' model, is introduced. This method introduces additional bias into the model with the aim of reducing variance such that errors are decreased overall. Compared with standard linear Bayesian inversion, the ridge technique seems to reduce both flux estimation errors and prediction errors. The second divergence from previous studies is that instead of dividing the world into geographically distinct regions and estimating the CO2 flux in each region, the flux space is divided conceptually into processes that contribute to the total global flux. Formulating the problem in this manner adds to the interpretability of the resultant estimates and attempts to shed light on the problem of attributing sources and sinks to their underlying mechanisms.

UR - http://www.scopus.com/inward/record.url?scp=33747105132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747105132&partnerID=8YFLogxK

U2 - 10.1111/j.1600-0889.2006.00189.x

DO - 10.1111/j.1600-0889.2006.00189.x

M3 - Article

VL - 58

SP - 279

EP - 292

JO - Tellus, Series B: Chemical and Physical Meteorology

JF - Tellus, Series B: Chemical and Physical Meteorology

SN - 0280-6509

IS - 4

ER -