25 Feb 2020
25 Feb 2020
Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model
- 1Key Laboratory of Urban Environment and Health, Key Laboratory of Urban Metabolism of Xiamen, Institute of Urban Environment, Chinese Academy of Sciences, CN 361021, China
- 2University of Chinese Academy of Sciences, CN 100049, China
- 3CSIRO, Waite Campus, Urrbrae, SA 5064, Australia
- 4State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, CN 100049, China
- 5Ningbo Urban Environment Observation and Research Station-NUEORS, Chinese Academy of Sciences, CN 315800, China
- 6Department of Geography, University of Hawai'i at Mānoa, Honolulu, HI 96822, USA
- 7Department of Earth and Environmental Sciences, University of British Columbia, Kelowna, BC V1V 1V7, Canada
- These authors contributed equally to this work.
- 1Key Laboratory of Urban Environment and Health, Key Laboratory of Urban Metabolism of Xiamen, Institute of Urban Environment, Chinese Academy of Sciences, CN 361021, China
- 2University of Chinese Academy of Sciences, CN 100049, China
- 3CSIRO, Waite Campus, Urrbrae, SA 5064, Australia
- 4State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, CN 100049, China
- 5Ningbo Urban Environment Observation and Research Station-NUEORS, Chinese Academy of Sciences, CN 315800, China
- 6Department of Geography, University of Hawai'i at Mānoa, Honolulu, HI 96822, USA
- 7Department of Earth and Environmental Sciences, University of British Columbia, Kelowna, BC V1V 1V7, Canada
- These authors contributed equally to this work.
Abstract. Aboveground biomass (AGB) estimates at the plot level plays a major part in connecting accurate single-tree AGB measurements to relatively difficult regional-scale AGB estimates. However, complex and spatially heterogeneous landscapes, where multiple environmental covariates (such as longitude, latitude, and forest structure) affect the spatial distribution of AGB, make upscaling of plot-level models more challenging. To address this challenge, this study proposes an approach that combines machine learning with spatial statistics to construct a more accurate plot-level AGB model. The study was conducted in a Eucalyptus plantation in Nanjing, China. We developed, evaluated, and compared the accuracy and performance of three different machine learning models [support vector machine (SVM), random forest (RF), and the radial basis function artificial neural network (RBF-ANN)], one spatial statistics model (P-BSHADE), and three combinations thereof (SVM & P-BSHADE, RF & P-BSHADE, RBF-ANN & P-BSHADE) for forest AGB estimates based on AGB data from 30 sample plots and their corresponding environmental covariates. The results show that the performance indices RMSE, nRMSE, MAE, and MRE of all combined models are substantially smaller than those of any individual models, with the RF & P-BSHADE combined method giving the smallest value. These results demonstrate clearly that combined models, especially the RF & P-BSHADE model, can improve the accuracy of plot-level AGB models and reduce uncertainty on plot-level AGB estimates or even on large-forested-landscape AGB estimates. These research results are important because they reduce the uncertainty in estimates of the regional carbon balance.
-
Withdrawal notice
This preprint has been withdrawn.
-
Preprint
(3574 KB)
-
Supplement
(4292 KB)
-
This preprint has been withdrawn.
- Preprint
(3574 KB) -
Supplement
(4292 KB) - BibTeX
- EndNote
Shaoqing Dai et al.
Interactive discussion


-
SC1: 'review comments on “Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model”', Wenli Huang, 07 Mar 2020
-
AC1: 'Response to SC1', Yin Ren, 21 Apr 2020
-
AC1: 'Response to SC1', Yin Ren, 21 Apr 2020
-
SC2: 'Interactive comment on “Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model” by Shaoqing Dai et al.', Wenli Huang, 14 Mar 2020
-
AC2: 'Response to SC2', Yin Ren, 21 Apr 2020
-
AC2: 'Response to SC2', Yin Ren, 21 Apr 2020
-
RC1: 'Review of bg-2020-36', Anonymous Referee #1, 25 Mar 2020
-
AC3: 'Response to RC1', Yin Ren, 21 Apr 2020
-
AC5: 'Additional response to RC1', Yin Ren, 05 Jun 2020
-
AC3: 'Response to RC1', Yin Ren, 21 Apr 2020
-
RC2: 'Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model', Anonymous Referee #2, 16 May 2020
-
AC4: 'Response to RC2', Yin Ren, 05 Jun 2020
-
AC4: 'Response to RC2', Yin Ren, 05 Jun 2020
Interactive discussion


-
SC1: 'review comments on “Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model”', Wenli Huang, 07 Mar 2020
-
AC1: 'Response to SC1', Yin Ren, 21 Apr 2020
-
AC1: 'Response to SC1', Yin Ren, 21 Apr 2020
-
SC2: 'Interactive comment on “Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model” by Shaoqing Dai et al.', Wenli Huang, 14 Mar 2020
-
AC2: 'Response to SC2', Yin Ren, 21 Apr 2020
-
AC2: 'Response to SC2', Yin Ren, 21 Apr 2020
-
RC1: 'Review of bg-2020-36', Anonymous Referee #1, 25 Mar 2020
-
AC3: 'Response to RC1', Yin Ren, 21 Apr 2020
-
AC5: 'Additional response to RC1', Yin Ren, 05 Jun 2020
-
AC3: 'Response to RC1', Yin Ren, 21 Apr 2020
-
RC2: 'Improving maps of forest aboveground biomass: A combined approach using machine learning with a spatial statistical model', Anonymous Referee #2, 16 May 2020
-
AC4: 'Response to RC2', Yin Ren, 05 Jun 2020
-
AC4: 'Response to RC2', Yin Ren, 05 Jun 2020
Shaoqing Dai et al.
Shaoqing Dai et al.
Viewed
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
378 | 132 | 10 | 520 | 52 | 12 | 17 |
- HTML: 378
- PDF: 132
- XML: 10
- Total: 520
- Supplement: 52
- BibTeX: 12
- EndNote: 17
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
This preprint has been withdrawn.
- Preprint
(3574 KB) - Metadata XML
-
Supplement
(4292 KB) - BibTeX
- EndNote