Parameter Estimation in Land Surface Models: Challenges and Opportunities With Data Assimilation and Machine Learning

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 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.

Authors

Institutions

Publication Details

Journal
Journal of Advances in Modeling Earth Systems
Published
2025-10-28
DOI
https://doi.org/10.1029/2024ms004733
Citations
4
Primary Topic
Plant Water Relations and Carbon Dynamics
Type
article
Field-Weighted Citation Impact
4.42
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Parameter Estimation in Land Surface Models: Challenges and Opportunities With Data Assimilation and Machine Learning

Daniel Kennedy, Rosie A. Fisher, Linnia Hawkins, Benjamin Mark Sanderson et al.
4 citations
Journal of Advances in Modeling Earth Systems
Plant Water Relations and Carbon Dynamics
4.42
article

Parameter Estimation in Land Surface Models: Challenges and Opportunities With Data Assimilation and Machine Learning

Daniel Kennedy, Rosie A. Fisher, Linnia Hawkins, Benjamin Mark Sanderson, John M. Zobitz, Tristan Quaife, Hannah M. Liddy, Noemi Vergopolan, Katherine Dagon, Toni Viskari, Mathew Williams, Cédric Bacour, Philippe Peylin, Nuno Carvalhais, Elizabeth Cooper, Michael C. Dietze, Istem Fer, Jana Kolassa, Pierre Gentine, Natasha MacBean, Ewan Pinnington, Nina Raoult, Christian Seiler, T. Luke Smallman, Marko Scholze, D. J. Moore, Thomas Kaminski, Andrew Roberts, Natalie Douglas
article en
4 citations

Abstract

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 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.

Journal of Advances in Modeling Earth SystemsVol. 17(11)
NSF National Center for Atmospheric Research (US), Boston University (US), Goddard Institute for Space Studies (US), Augsburg University (US), Western University (CA), Finnish Meteorological Institute (FI), Centre National de la Recherche Scientifique (FR), Planetary Science Institute (US), Goddard Space Flight Center (US), University of Arizona (US), European Centre for Medium-Range Weather Forecasts (GB), Lund University (SE), Université de Versailles Saint-Quentin-en-Yvelines (FR), Queen's University (CA), University of Exeter (GB), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), Université Paris-Saclay (FR), Earth Island Institute (US), University of Massachusetts Boston (US), UK Centre for Ecology & Hydrology (GB), Kennedy Center (DK), CICERO Center for International Climate Research (NO), Planetary Systems (United States) (US), Inversa Systems (Canada) (CA), Joint Research Centre (IT), Laboratoire des Sciences du Climat et de l'Environnement (FR), National Centre for Earth Observation (GB), CEA Paris-Saclay (FR), Science Systems and Applications (United States) (US), Max Planck Institute for Biogeochemistry (DE), University of Reading (GB), Rice University (US), Columbia University (US), Universidade Nova de Lisboa (PT), University of Edinburgh (GB)
Openalex Percentile: Top 5%
Plant Water Relations and Carbon Dynamics
4.42
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.