A differentiable, physics-informed ecosystem modeling and learning framework for large-scale inverse problems: demonstration with photosynthesis simulations
<p>Photosynthesis plays an important role in carbon, nitrogen, and water cycles. Ecosystem models for photosynthesis are characterized by many parameters that are obtained from limited in situ measurements and applied to the same plant types. Previous site-by-site calibration approaches could...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-07-01
|
| Series: | Biogeosciences |
| Online Access: | https://bg.copernicus.org/articles/20/2671/2023/bg-20-2671-2023.pdf |
| Summary: | <p>Photosynthesis plays an important role in carbon,
nitrogen, and water cycles. Ecosystem models for photosynthesis are
characterized by many parameters that are obtained from limited in situ
measurements and applied to the same plant types. Previous site-by-site
calibration approaches could not leverage big data and faced issues like
overfitting or parameter non-uniqueness. Here we developed an end-to-end
programmatically differentiable (meaning gradients of outputs to variables
used in the model can be obtained efficiently and accurately) version of the
photosynthesis process representation within the Functionally Assembled
Terrestrial Ecosystem Simulator (FATES) model. As a genre of
physics-informed machine learning (ML), differentiable models couple
physics-based formulations to neural networks (NNs) that learn parameterizations
(and potentially processes) from observations, here photosynthesis rates. We
first demonstrated that the framework was able to correctly recover multiple assumed
parameter values concurrently using synthetic training data. Then, using a
real-world dataset consisting of many different plant functional types (PFTs), we
learned parameters that performed substantially better and greatly reduced
biases compared to literature values. Further, the framework allowed us to
gain insights at a large scale. Our results showed that the carboxylation
rate at 25 <span class="inline-formula"><sup>∘</sup></span>C (<span class="inline-formula"><i>V</i><sub>c,max25</sub></span>) was more impactful than a factor
representing water limitation, although tuning both was helpful in
addressing biases with the default values. This framework could potentially
enable substantial improvement in our capability to learn parameters and
reduce biases for ecosystem modeling at large scales.</p> |
|---|---|
| ISSN: | 1726-4170 1726-4189 |