Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 6.58 MB
Add to list
  1. Search results
  2. Variability and uncertainty in flux-s...

Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing : a systematic evaluation

Haiyang Shi, Geping Luo, Olaf Hellwich, Mingjuan Xie (UGent) , Chen Zhang, Yu Zhang, Yuangang Wang, Xiuliang Yuan, Xiaofei Ma, Wenqiang Zhang (UGent) , et al.
(2022) BIOGEOSCIENCES. 19(16). p.3739-3756
Author
Organization
Abstract
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 R-2 values, especially when the timescale exceeds the monthly scale. Half-hourly models (average R-2 = 0.73) were significantly more accurate than daily models (average R-2 = 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 R-2 = 0.37) with multiple PFTs, more sites, and a large span of years correspond to lower R 2 values than studies at local (average R-2 = 0.69) and regional (average R-2 = 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.
Keywords
CARBON-DIOXIDE, FORESTS, METAANALYSIS, RESPONSES, LANDSAT

Downloads

  • Download
    bg-19-3739-2022.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 6.58 MB

Citation

Please use this url to cite or link to this publication:

MLA
Shi, Haiyang, et al. “Variability and Uncertainty in Flux-Site-Scale Net Ecosystem Exchange Simulations Based on Machine Learning and Remote Sensing : A Systematic Evaluation.” BIOGEOSCIENCES, vol. 19, no. 16, 2022, pp. 3739–56, doi:10.5194/bg-19-3739-2022.
APA
Shi, H., Luo, G., Hellwich, O., Xie, M., Zhang, C., Zhang, Y., … Van de Voorde, T. (2022). Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing : a systematic evaluation. BIOGEOSCIENCES, 19(16), 3739–3756. https://doi.org/10.5194/bg-19-3739-2022
Chicago author-date
Shi, Haiyang, Geping Luo, Olaf Hellwich, Mingjuan Xie, Chen Zhang, Yu Zhang, Yuangang Wang, et al. 2022. “Variability and Uncertainty in Flux-Site-Scale Net Ecosystem Exchange Simulations Based on Machine Learning and Remote Sensing : A Systematic Evaluation.” BIOGEOSCIENCES 19 (16): 3739–56. https://doi.org/10.5194/bg-19-3739-2022.
Chicago author-date (all authors)
Shi, Haiyang, Geping Luo, Olaf Hellwich, Mingjuan Xie, Chen Zhang, Yu Zhang, Yuangang Wang, Xiuliang Yuan, Xiaofei Ma, Wenqiang Zhang, Alishir Kurban, Philippe De Maeyer, and Tim Van de Voorde. 2022. “Variability and Uncertainty in Flux-Site-Scale Net Ecosystem Exchange Simulations Based on Machine Learning and Remote Sensing : A Systematic Evaluation.” BIOGEOSCIENCES 19 (16): 3739–3756. doi:10.5194/bg-19-3739-2022.
Vancouver
1.
Shi H, Luo G, Hellwich O, Xie M, Zhang C, Zhang Y, et al. Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing : a systematic evaluation. BIOGEOSCIENCES. 2022;19(16):3739–56.
IEEE
[1]
H. Shi et al., “Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing : a systematic evaluation,” BIOGEOSCIENCES, vol. 19, no. 16, pp. 3739–3756, 2022.
@article{01GKGQWDWNNVYGM17Q4MVV1ZSB,
  abstract     = {{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 R-2 values, especially when the timescale exceeds the monthly scale. Half-hourly models (average R-2 = 0.73) were significantly more accurate than daily models (average R-2 = 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 R-2 = 0.37) with multiple PFTs, more sites, and a large span of years correspond to lower R 2 values than studies at local (average R-2 = 0.69) and regional (average R-2 = 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.}},
  author       = {{Shi, Haiyang and  Luo, Geping and  Hellwich, Olaf and Xie, Mingjuan and  Zhang, Chen and  Zhang, Yu and  Wang, Yuangang and  Yuan, Xiuliang and  Ma, Xiaofei and Zhang, Wenqiang and  Kurban, Alishir and De Maeyer, Philippe and Van de Voorde, Tim}},
  issn         = {{1726-4170}},
  journal      = {{BIOGEOSCIENCES}},
  keywords     = {{CARBON-DIOXIDE,FORESTS,METAANALYSIS,RESPONSES,LANDSAT}},
  language     = {{eng}},
  number       = {{16}},
  pages        = {{3739--3756}},
  title        = {{Variability and uncertainty in flux-site-scale net ecosystem exchange simulations based on machine learning and remote sensing : a systematic evaluation}},
  url          = {{http://doi.org/10.5194/bg-19-3739-2022}},
  volume       = {{19}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: