Preprints
https://doi.org/10.5194/bg-2022-46
https://doi.org/10.5194/bg-2022-46
 
24 Mar 2022
24 Mar 2022
Status: this preprint is currently under review for the journal BG.

Variability and Uncertainty in Flux-Site Scale Net Ecosystem Exchange Simulations Based on Machine Learning and Remote Sensing: A Systematic Evaluation

Haiyang Shi1,2,4,5, Geping Luo1,2,3,5, Olaf Hellwich6, Mingjuan Xie1,2,4,5, Chen Zhang1,2, Yu Zhang1,2, Yuangang Wang1,2, Xiuliang Yuan1, Xiaofei Ma1, Wenqiang Zhang1,2,4,5, Alishir Kurban1,2,3,5, Philippe De Maeyer1,2,4,5, and Tim Van de Voorde4,5 Haiyang Shi et al.
  • 1State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, Xinjiang, 830011, China
  • 2University of Chinese Academy of Sciences, 19 (A) Yuquan Road, Beijing, 100049, China
  • 3Research Centre for Ecology and Environment of Central Asia, Chinese Academy of Sciences, Urumqi, China
  • 4Department of Geography, Ghent University, Ghent 9000, Belgium
  • 5Sino-Belgian Joint Laboratory of Geo-Information, Ghent, Belgium and Urumqi, China
  • 6Department of Computer Vision & Remote Sensing, Technische Universität Berlin, 10587 Berlin, Germany

Abstract. Net ecosystem exchange (NEE) is an important indicator of carbon cycling in terrestrial ecosystems. Many previous studies have combined flux observations, 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. Total 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 time scales have lower average R-squared, especially when the time scale exceeds the monthly scale. Half-hourly models (average R-squared = 0.73) were significantly more accurate than daily models (average R-squared = 0.5). There are significant differences in the predictors used and their impacts on model accuracy for different plant functional types (PFT). Studies at continental and global scales (average R-squared = 0.37) with multiple PFTs, more sites, and a large span of years correspond to lower R-squared than studies at local (average R-squared = 0.69) and regional scales (average R-squared = 0.7). 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. The results of this study may also be applicable to the prediction of other carbon fluxes such as methane.

Haiyang Shi et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on bg-2022-46', Anonymous Referee #1, 06 Apr 2022
  • RC2: 'Comment on bg-2022-46', Anonymous Referee #2, 09 Apr 2022
    • AC2: 'Reply on RC2', Haiyang Shi, 07 May 2022
  • RC3: 'Comment on bg-2022-46', Anonymous Referee #3, 09 Apr 2022

Haiyang Shi et al.

Haiyang Shi et al.

Viewed

Total article views: 491 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
374 95 22 491 32 8 11
  • HTML: 374
  • PDF: 95
  • XML: 22
  • Total: 491
  • Supplement: 32
  • BibTeX: 8
  • EndNote: 11
Views and downloads (calculated since 24 Mar 2022)
Cumulative views and downloads (calculated since 24 Mar 2022)

Viewed (geographical distribution)

Total article views: 472 (including HTML, PDF, and XML) Thereof 472 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 May 2022
Download
Short summary
A number of studies have been conducted by using machine learning approaches to simulate carbon fluxes. We performed a meta-analysis of these NEE simulations. Random forests and support vector machines performed better than other algorithms. Models with larger time scales had a lower accuracy. For different plant functional types (PFTs), there were significant differences in the predictors used and their effects on model accuracy.
Altmetrics