Parameter Estimation in Land Surface Models : Challenges and Opportunities With Data Assimilation and Machine Learning
(2025) In Journal of Advances in Modeling Earth Systems 17(11).- Abstract
Accurately predicting terrestrial ecosystem responses to climate change over long-timescales is crucial for addressing global challenges. This relies on mechanistic modeling of ecosystem processes through land surface models (LSMs). Despite their importance, LSMs face significant uncertainties due to poorly constrained parameters, especially in carbon cycle predictions. This paper reviews the progress made in using data assimilation (DA) for LSM parameter optimization, focusing on carbon-water-vegetation interactions, as well as discussing the technical challenges faced by the community. These challenges include identifying sensitive model parameters and their prior distributions, characterizing errors due to observation biases and... (More)
Accurately predicting terrestrial ecosystem responses to climate change over long-timescales is crucial for addressing global challenges. This relies on mechanistic modeling of ecosystem processes through land surface models (LSMs). Despite their importance, LSMs face significant uncertainties due to poorly constrained parameters, especially in carbon cycle predictions. This paper reviews the progress made in using data assimilation (DA) for LSM parameter optimization, focusing on carbon-water-vegetation interactions, as well as discussing the technical challenges faced by the community. These challenges include identifying sensitive model parameters and their prior distributions, characterizing errors due to observation biases and model-data inconsistencies, developing observation operators to interface between the model and the observations, tackling spatial and temporal heterogeneity as well as dealing with large and multiple data sets, and including the spin-up and historical period in the assimilation window. We outline how machine learning (ML) can help address these issues, proposing different avenues for future work that integrate ML and DA to reduce uncertainties in LSMs. We conclude by highlighting future priorities, including the need for international collaborations, to fully leverage the wealth of available Earth observation data sets, harness ML advances, and enhance the predictive capabilities of LSMs.
(Less)
- author
- Raoult, Nina
; Douglas, Natalie
; MacBean, Natasha
; Kolassa, Jana
; Quaife, Tristan
; Roberts, Andrew G.
; Fisher, Rosie
; Fer, Istem
; Bacour, Cédric
; Dagon, Katherine
; Hawkins, Linnia
; Carvalhais, Nuno
; Cooper, Elizabeth
; Dietze, Michael C.
; Gentine, Pierre
; Kaminski, Thomas
; Kennedy, Daniel
; Liddy, Hannah M.
; Moore, David J.P.
; Peylin, Philippe
; Pinnington, Ewan
; Sanderson, Benjamin
; Scholze, Marko
LU
; Seiler, Christian
; Smallman, T. Luke
; Vergopolan, Noemi
; Viskari, Toni
; Williams, Mathew
and Zobitz, John
(Less) - organization
- publishing date
- 2025-11
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- data assimilation, land surface modeling, machine learning, model calibration, parameter estimation, uncertainty quantification
- in
- Journal of Advances in Modeling Earth Systems
- volume
- 17
- issue
- 11
- article number
- e2024MS004733
- publisher
- Wiley-Blackwell
- external identifiers
-
- scopus:105020242900
- ISSN
- 1942-2466
- DOI
- 10.1029/2024MS004733
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 The Author(s). Journal of Advances in Modeling Earth Systems published by Wiley Periodicals LLC on behalf of American Geophysical Union.
- id
- 9e14ad44-457e-454c-b9c0-2fc19f6e7ee2
- date added to LUP
- 2025-12-16 10:22:22
- date last changed
- 2025-12-17 08:42:03
@article{9e14ad44-457e-454c-b9c0-2fc19f6e7ee2,
abstract = {{<p>Accurately predicting terrestrial ecosystem responses to climate change over long-timescales is crucial for addressing global challenges. This relies on mechanistic modeling of ecosystem processes through land surface models (LSMs). Despite their importance, LSMs face significant uncertainties due to poorly constrained parameters, especially in carbon cycle predictions. This paper reviews the progress made in using data assimilation (DA) for LSM parameter optimization, focusing on carbon-water-vegetation interactions, as well as discussing the technical challenges faced by the community. These challenges include identifying sensitive model parameters and their prior distributions, characterizing errors due to observation biases and model-data inconsistencies, developing observation operators to interface between the model and the observations, tackling spatial and temporal heterogeneity as well as dealing with large and multiple data sets, and including the spin-up and historical period in the assimilation window. We outline how machine learning (ML) can help address these issues, proposing different avenues for future work that integrate ML and DA to reduce uncertainties in LSMs. We conclude by highlighting future priorities, including the need for international collaborations, to fully leverage the wealth of available Earth observation data sets, harness ML advances, and enhance the predictive capabilities of LSMs.</p>}},
author = {{Raoult, Nina and Douglas, Natalie and MacBean, Natasha and Kolassa, Jana and Quaife, Tristan and Roberts, Andrew G. and Fisher, Rosie and Fer, Istem and Bacour, Cédric and Dagon, Katherine and Hawkins, Linnia and Carvalhais, Nuno and Cooper, Elizabeth and Dietze, Michael C. and Gentine, Pierre and Kaminski, Thomas and Kennedy, Daniel and Liddy, Hannah M. and Moore, David J.P. and Peylin, Philippe and Pinnington, Ewan and Sanderson, Benjamin and Scholze, Marko and Seiler, Christian and Smallman, T. Luke and Vergopolan, Noemi and Viskari, Toni and Williams, Mathew and Zobitz, John}},
issn = {{1942-2466}},
keywords = {{data assimilation; land surface modeling; machine learning; model calibration; parameter estimation; uncertainty quantification}},
language = {{eng}},
number = {{11}},
publisher = {{Wiley-Blackwell}},
series = {{Journal of Advances in Modeling Earth Systems}},
title = {{Parameter Estimation in Land Surface Models : Challenges and Opportunities With Data Assimilation and Machine Learning}},
url = {{http://dx.doi.org/10.1029/2024MS004733}},
doi = {{10.1029/2024MS004733}},
volume = {{17}},
year = {{2025}},
}