Home > Research > Publications & Outputs > Combining LiDAR and hyperspectral data for abov...

Links

Text available via DOI:

View graph of relations

Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. / de Almeida, C.T.; Galvão, L.S.; Aragão, L.E.D.O.C.E. et al.

In: Remote Sensing of Environment, Vol. 232, 111323, 01.10.2019.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

de Almeida, CT, Galvão, LS, Aragão, LEDOCE, Ometto, JPHB, Jacon, AD, Pereira, FRDS, Sato, LY, Lopes, AP, Graça, PMLDA, Silva, CVDJ, Ferreira-Ferreira, J & Longo, M 2019, 'Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms', Remote Sensing of Environment, vol. 232, 111323. https://doi.org/10.1016/j.rse.2019.111323

APA

de Almeida, C. T., Galvão, L. S., Aragão, L. E. D. O. C. E., Ometto, J. P. H. B., Jacon, A. D., Pereira, F. R. D. S., Sato, L. Y., Lopes, A. P., Graça, P. M. L. D. A., Silva, C. V. D. J., Ferreira-Ferreira, J., & Longo, M. (2019). Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. Remote Sensing of Environment, 232, [111323]. https://doi.org/10.1016/j.rse.2019.111323

Vancouver

de Almeida CT, Galvão LS, Aragão LEDOCE, Ometto JPHB, Jacon AD, Pereira FRDS et al. Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. Remote Sensing of Environment. 2019 Oct 1;232:111323. Epub 2019 Aug 7. doi: 10.1016/j.rse.2019.111323

Author

de Almeida, C.T. ; Galvão, L.S. ; Aragão, L.E.D.O.C.E. et al. / Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. In: Remote Sensing of Environment. 2019 ; Vol. 232.

Bibtex

@article{56965ea2a5d34df5bac0df6391b000cd,
title = "Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms",
abstract = "Accurate estimates of aboveground biomass (AGB) in tropical forests are critical for supporting strategies of ecosystem functioning conservation and climate change mitigation. However, such estimates at regional and local scales are still highly uncertain. Airborne Light Detection And Ranging (LiDAR) and Hyperspectral Imaging (HSI) can characterize the structural and functional diversity of forests with high accuracy at a sub-meter resolution, and potentially improve the AGB estimations. In this study, we compared the ability of different data sources (airborne LiDAR and HSI, and their combination) and regression methods (linear model - LM, linear model with ridge regularization - LMR, Support Vector Regression - SVR, Random Forest - RF, Stochastic Gradient Boosting - SGB, and Cubist - CB) to improve AGB predictions in the Brazilian Amazon. We used georeferenced inventory data from 132 sample plots to obtain a reference field AGB and calculated 333 metrics (45 from LiDAR and 288 from HSI) that could be used as predictors for statistical AGB models. We submitted the metrics to a correlation filtering followed by a feature selection procedure (recursive feature elimination) to optimize the performance of the models and to reduce their complexity. Results showed that both LiDAR and HSI data used alone provided relatively high accurate models if adequate metrics and algorithms are chosen (RMSE = 67.6 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best LiDAR model; RMSE = 68.1 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best HSI model). However, HSI-only models required more metrics (5–12) than LiDAR-only models (2–5). Models combining metrics from both datasets resulted in more accurate AGB estimates, regardless of the regression method (RMSE = 57.7 Mg.ha−1, RMSE% = 31%, R2 = 0.70, for the best model). The most important LiDAR metrics for estimating AGB were related to the upper canopy cover and tree height percentiles, while the most important HSI metrics were associated with the near infrared and shortwave infrared spectral regions, particularly the leaf/canopy water and lignin-cellulose absorption bands. Finally, an analysis of variance (ANOVA) showed that the remote sensing data source (LiDAR, HSI, or their combination) had a greater effect size than the regression algorithms. Thus, no single algorithm outperformed the others, although the LM method was less suitable when applied to the HSI and hybrid datasets. Results show that the synergistic use of LiDAR and hyperspectral data has great potential for improving the accuracy of the biomass estimates in the Brazilian Amazon.",
keywords = "Hyperspectral remote sensing, Laser scanning, Data integration, Tropical forest, Carbon stock",
author = "{de Almeida}, C.T. and L.S. Galv{\~a}o and L.E.D.O.C.E. Arag{\~a}o and J.P.H.B. Ometto and A.D. Jacon and F.R.D.S. Pereira and L.Y. Sato and A.P. Lopes and P.M.L.D.A. Gra{\c c}a and C.V.D.J. Silva and J. Ferreira-Ferreira and M. Longo",
year = "2019",
month = oct,
day = "1",
doi = "10.1016/j.rse.2019.111323",
language = "English",
volume = "232",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",

}

RIS

TY - JOUR

T1 - Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms

AU - de Almeida, C.T.

AU - Galvão, L.S.

AU - Aragão, L.E.D.O.C.E.

AU - Ometto, J.P.H.B.

AU - Jacon, A.D.

AU - Pereira, F.R.D.S.

AU - Sato, L.Y.

AU - Lopes, A.P.

AU - Graça, P.M.L.D.A.

AU - Silva, C.V.D.J.

AU - Ferreira-Ferreira, J.

AU - Longo, M.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Accurate estimates of aboveground biomass (AGB) in tropical forests are critical for supporting strategies of ecosystem functioning conservation and climate change mitigation. However, such estimates at regional and local scales are still highly uncertain. Airborne Light Detection And Ranging (LiDAR) and Hyperspectral Imaging (HSI) can characterize the structural and functional diversity of forests with high accuracy at a sub-meter resolution, and potentially improve the AGB estimations. In this study, we compared the ability of different data sources (airborne LiDAR and HSI, and their combination) and regression methods (linear model - LM, linear model with ridge regularization - LMR, Support Vector Regression - SVR, Random Forest - RF, Stochastic Gradient Boosting - SGB, and Cubist - CB) to improve AGB predictions in the Brazilian Amazon. We used georeferenced inventory data from 132 sample plots to obtain a reference field AGB and calculated 333 metrics (45 from LiDAR and 288 from HSI) that could be used as predictors for statistical AGB models. We submitted the metrics to a correlation filtering followed by a feature selection procedure (recursive feature elimination) to optimize the performance of the models and to reduce their complexity. Results showed that both LiDAR and HSI data used alone provided relatively high accurate models if adequate metrics and algorithms are chosen (RMSE = 67.6 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best LiDAR model; RMSE = 68.1 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best HSI model). However, HSI-only models required more metrics (5–12) than LiDAR-only models (2–5). Models combining metrics from both datasets resulted in more accurate AGB estimates, regardless of the regression method (RMSE = 57.7 Mg.ha−1, RMSE% = 31%, R2 = 0.70, for the best model). The most important LiDAR metrics for estimating AGB were related to the upper canopy cover and tree height percentiles, while the most important HSI metrics were associated with the near infrared and shortwave infrared spectral regions, particularly the leaf/canopy water and lignin-cellulose absorption bands. Finally, an analysis of variance (ANOVA) showed that the remote sensing data source (LiDAR, HSI, or their combination) had a greater effect size than the regression algorithms. Thus, no single algorithm outperformed the others, although the LM method was less suitable when applied to the HSI and hybrid datasets. Results show that the synergistic use of LiDAR and hyperspectral data has great potential for improving the accuracy of the biomass estimates in the Brazilian Amazon.

AB - Accurate estimates of aboveground biomass (AGB) in tropical forests are critical for supporting strategies of ecosystem functioning conservation and climate change mitigation. However, such estimates at regional and local scales are still highly uncertain. Airborne Light Detection And Ranging (LiDAR) and Hyperspectral Imaging (HSI) can characterize the structural and functional diversity of forests with high accuracy at a sub-meter resolution, and potentially improve the AGB estimations. In this study, we compared the ability of different data sources (airborne LiDAR and HSI, and their combination) and regression methods (linear model - LM, linear model with ridge regularization - LMR, Support Vector Regression - SVR, Random Forest - RF, Stochastic Gradient Boosting - SGB, and Cubist - CB) to improve AGB predictions in the Brazilian Amazon. We used georeferenced inventory data from 132 sample plots to obtain a reference field AGB and calculated 333 metrics (45 from LiDAR and 288 from HSI) that could be used as predictors for statistical AGB models. We submitted the metrics to a correlation filtering followed by a feature selection procedure (recursive feature elimination) to optimize the performance of the models and to reduce their complexity. Results showed that both LiDAR and HSI data used alone provided relatively high accurate models if adequate metrics and algorithms are chosen (RMSE = 67.6 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best LiDAR model; RMSE = 68.1 Mg.ha−1, RMSE% = 36%, R2 = 0.58, for the best HSI model). However, HSI-only models required more metrics (5–12) than LiDAR-only models (2–5). Models combining metrics from both datasets resulted in more accurate AGB estimates, regardless of the regression method (RMSE = 57.7 Mg.ha−1, RMSE% = 31%, R2 = 0.70, for the best model). The most important LiDAR metrics for estimating AGB were related to the upper canopy cover and tree height percentiles, while the most important HSI metrics were associated with the near infrared and shortwave infrared spectral regions, particularly the leaf/canopy water and lignin-cellulose absorption bands. Finally, an analysis of variance (ANOVA) showed that the remote sensing data source (LiDAR, HSI, or their combination) had a greater effect size than the regression algorithms. Thus, no single algorithm outperformed the others, although the LM method was less suitable when applied to the HSI and hybrid datasets. Results show that the synergistic use of LiDAR and hyperspectral data has great potential for improving the accuracy of the biomass estimates in the Brazilian Amazon.

KW - Hyperspectral remote sensing

KW - Laser scanning

KW - Data integration

KW - Tropical forest

KW - Carbon stock

U2 - 10.1016/j.rse.2019.111323

DO - 10.1016/j.rse.2019.111323

M3 - Journal article

VL - 232

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

M1 - 111323

ER -