Differentiable land model reveals global environmental controls on latent ecological functions
4 affiliations
- 1Department of Earth and Environmental Engineering, Columbia University, New York, NY, USA. [email protected]
- 2Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA
- 3Department of Earth and Environmental Engineering, Columbia University, New York, NY, USA
- 4Department of Earth and Environmental Engineering, Columbia University, New York, NY, USA. [email protected]
Abstract
The spatial distributions of plant functional traits observed today are living imprints of current environmental gradients and past selection, offering insight into how plants have adapted to their environments. What remains insufficiently understood is how traits combine and coordinate across environments, and whether such coordination reflects organizing principles in ecology that can improve modeling of ecosystem functional diversity and decadal-scale carbon exchange. Here we present DifferLand, a differentiable hybrid model that learns high-dimensional, coordinated environment-trait relationships directly from multi-modal satellite and in situ observations. DifferLand reveals a small number of latent axes that represent how suites of plant traits jointly shape vegetation dynamics and carbon-water fluxes, enabling the model to capture both long-term adaptation patterns and short-term responses to meteorological variability, and to outperform models that rely solely on plant functional types in spatial generalization. The spatialization network learns nonlinear interactions between plant functional attributes and environmental gradients, organizing latent ecological parameters that represent functional traits at the global scale. This latent environment-trait structure reveals large-scale patterns of ecosystem functional diversity and improves the spatial generalization of terrestrial biosphere models.
Related
- Interpretable machine learning reveals environmental controls on carbon-water flux dynamics in a humid subtropical evergreen forest
- Stage-dependent shifts in climate and human controls on carbon storage and habitat quality under ecological restoration and urbanization
- Environmental controls on the detectability of hydrodynamic changes induced by offshore wind farm structures
- Energetic Controls on Biodegradation of Organic Matter from Diverse Environmental Sources.
- Microplastics in agricultural soils, their sources, environmental impacts, ecological risks, and mitigation strategies
BibTeX
@article{fang2026differentiable,
title = {{Differentiable land model reveals global environmental controls on latent ecological functions}},
author = {Jianing Fang and Kevin Bowman and Wenli Zhao and Xu Lian and Pierre Gentine},
journal = {Nature Communications},
year = {2026},
month = may,
doi = {10.1038/s41467-026-73395-4},
url = {https://doi.org/10.1038/s41467-026-73395-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - Differentiable land model reveals global environmental controls on latent ecological functions
AU - Jianing Fang
AU - Kevin Bowman
AU - Wenli Zhao
AU - Xu Lian
AU - Pierre Gentine
PY - 2026
DA - 2026/05/21
JO - Nature Communications
DO - 10.1038/s41467-026-73395-4
UR - https://doi.org/10.1038/s41467-026-73395-4
AB - The spatial distributions of plant functional traits observed today are living imprints of current environmental gradients and past selection, offering insight into how plants have adapted to their environments. What remains insufficiently understood is how traits combine and coordinate across environments, and whether such coordination reflects organizing principles in ecology that can improve modeling of ecosystem functional diversity and decadal-scale carbon exchange. Here we present DifferLand, a differentiable hybrid model that learns high-dimensional, coordinated environment-trait relationships directly from multi-modal satellite and in situ observations. DifferLand reveals a small number of latent axes that represent how suites of plant traits jointly shape vegetation dynamics and carbon-water fluxes, enabling the model to capture both long-term adaptation patterns and short-term responses to meteorological variability, and to outperform models that rely solely on plant functional types in spatial generalization. The spatialization network learns nonlinear interactions between plant functional attributes and environmental gradients, organizing latent ecological parameters that represent functional traits at the global scale. This latent environment-trait structure reveals large-scale patterns of ecosystem functional diversity and improves the spatial generalization of terrestrial biosphere models.
SN - 2041-1723
ER -