Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing: a systematic evaluation
<p>Net ecosystem exchange (NEE) is an important indicator of carbon cycling in terrestrial ecosystems. Many previous studies have combined flux observations and meteorological, biophysical, and ancillary predictors using machine learning to simulate the site-scale NEE. However, systematic eval...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-08-01
|
| Series: | Biogeosciences |
| Online Access: | https://bg.copernicus.org/articles/19/3739/2022/bg-19-3739-2022.pdf |
| Summary: | <p>Net ecosystem exchange (NEE) is an important indicator of
carbon cycling in terrestrial ecosystems. Many previous studies have
combined flux observations and meteorological, biophysical, and ancillary
predictors using machine learning to simulate the site-scale NEE. However,
systematic evaluation of the performance of such models is limited.
Therefore, we performed a meta-analysis of these NEE simulations. A total of
40 such studies and 178 model records were included. The impacts of various
features throughout the modeling process on the accuracy of the model were
evaluated. Random forests and support vector machines performed better than
other algorithms. Models with larger timescales have lower average
<span class="inline-formula"><i>R</i><sup>2</sup></span> values, especially when the timescale exceeds the monthly scale.
Half-hourly models (average <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.73) were significantly more
accurate than daily models (average <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.5). There are
significant differences in the predictors used and their impacts on model
accuracy for different plant functional types (PFTs). Studies at continental
and global scales (average <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.37) with multiple PFTs, more
sites, and a large span of years correspond to lower <span class="inline-formula"><i>R</i><sup>2</sup></span> values than studies
at local (average <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.69) and regional (average <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.7) scales. Also, the site-scale NEE predictions need more focus on the
internal heterogeneity of the NEE dataset and the matching of the training
set and validation set.</p> |
|---|---|
| ISSN: | 1726-4170 1726-4189 |