Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms
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...
| Autor principal: | Almeida, Catherine Torres de |
|---|---|
| Outros Autores: | Galvão, L. S., Aragao, L. E.O.C., Ometto, Jean Pierre Henry Balbaud, Jacon, Aline Daniele, Pereira, Francisca Rocha de Souza, Sato, Luciane Yumie, Lopes, Aline Pontes, Graça, Paulo Maurício Lima Alencastro de, Silva, Camila Valéria de Jesus, Ferreira-Ferreira, Jefferson, Longo, Marcos |
| Grau: | Artigo |
| Idioma: | English |
| Publicado em: |
Remote Sensing of Environment
2020
|
| Assuntos: | |
| Acesso em linha: |
https://repositorio.inpa.gov.br/handle/1/16614 |
| id |
oai:repositorio:1-16614 |
|---|---|
| recordtype |
dspace |
| spelling |
oai:repositorio:1-16614 Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms Almeida, Catherine Torres de Galvão, L. S. Aragao, L. E.O.C. Ometto, Jean Pierre Henry Balbaud Jacon, Aline Daniele Pereira, Francisca Rocha de Souza Sato, Luciane Yumie Lopes, Aline Pontes Graça, Paulo Maurício Lima Alencastro de Silva, Camila Valéria de Jesus Ferreira-Ferreira, Jefferson Longo, Marcos Analysis Of Variance (anova) Biomass Climate Change Data Integration Decision Trees Forestry Hyperspectral Imaging Infrared Devices Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Stochastic Models Stochastic Systems Water Absorption Carbon Stocks Hyperspectral Remote Sensing Laser Scanning Light Detection And Ranging Recursive Feature Elimination Stochastic Gradient Boosting Support Vector Regression (svr) Tropical Forest Optical Radar Aboveground Biomass Algorithm Data Assimilation Laser Method Lidar Modeling Remote Sensing Spectral Analysis Tropical Forest Variance Analysis Biomass Forestry Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Amazonia Brasil 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. © 2019 Elsevier Inc. 2020-06-15T21:35:26Z 2020-06-15T21:35:26Z 2019 Artigo https://repositorio.inpa.gov.br/handle/1/16614 10.1016/j.rse.2019.111323 en Volume 232 Restrito Remote Sensing of Environment |
| institution |
Instituto Nacional de Pesquisas da Amazônia - Repositório Institucional |
| collection |
INPA-RI |
| language |
English |
| topic |
Analysis Of Variance (anova) Biomass Climate Change Data Integration Decision Trees Forestry Hyperspectral Imaging Infrared Devices Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Stochastic Models Stochastic Systems Water Absorption Carbon Stocks Hyperspectral Remote Sensing Laser Scanning Light Detection And Ranging Recursive Feature Elimination Stochastic Gradient Boosting Support Vector Regression (svr) Tropical Forest Optical Radar Aboveground Biomass Algorithm Data Assimilation Laser Method Lidar Modeling Remote Sensing Spectral Analysis Tropical Forest Variance Analysis Biomass Forestry Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Amazonia Brasil |
| spellingShingle |
Analysis Of Variance (anova) Biomass Climate Change Data Integration Decision Trees Forestry Hyperspectral Imaging Infrared Devices Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Stochastic Models Stochastic Systems Water Absorption Carbon Stocks Hyperspectral Remote Sensing Laser Scanning Light Detection And Ranging Recursive Feature Elimination Stochastic Gradient Boosting Support Vector Regression (svr) Tropical Forest Optical Radar Aboveground Biomass Algorithm Data Assimilation Laser Method Lidar Modeling Remote Sensing Spectral Analysis Tropical Forest Variance Analysis Biomass Forestry Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Amazonia Brasil Almeida, Catherine Torres de Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| topic_facet |
Analysis Of Variance (anova) Biomass Climate Change Data Integration Decision Trees Forestry Hyperspectral Imaging Infrared Devices Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Stochastic Models Stochastic Systems Water Absorption Carbon Stocks Hyperspectral Remote Sensing Laser Scanning Light Detection And Ranging Recursive Feature Elimination Stochastic Gradient Boosting Support Vector Regression (svr) Tropical Forest Optical Radar Aboveground Biomass Algorithm Data Assimilation Laser Method Lidar Modeling Remote Sensing Spectral Analysis Tropical Forest Variance Analysis Biomass Forestry Lithium Compounds Regression Analysis Remote Sensing Spectroscopy Amazonia Brasil |
| description |
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. © 2019 Elsevier Inc. |
| format |
Artigo |
| author |
Almeida, Catherine Torres de |
| author2 |
Galvão, L. S. Aragao, L. E.O.C. Ometto, Jean Pierre Henry Balbaud Jacon, Aline Daniele Pereira, Francisca Rocha de Souza Sato, Luciane Yumie Lopes, Aline Pontes Graça, Paulo Maurício Lima Alencastro de Silva, Camila Valéria de Jesus Ferreira-Ferreira, Jefferson Longo, Marcos |
| author2Str |
Galvão, L. S. Aragao, L. E.O.C. Ometto, Jean Pierre Henry Balbaud Jacon, Aline Daniele Pereira, Francisca Rocha de Souza Sato, Luciane Yumie Lopes, Aline Pontes Graça, Paulo Maurício Lima Alencastro de Silva, Camila Valéria de Jesus Ferreira-Ferreira, Jefferson Longo, Marcos |
| title |
Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| title_short |
Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| title_full |
Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| title_fullStr |
Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| title_full_unstemmed |
Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms |
| title_sort |
combining lidar and hyperspectral data for aboveground biomass modeling in the brazilian amazon using different regression algorithms |
| publisher |
Remote Sensing of Environment |
| publishDate |
2020 |
| url |
https://repositorio.inpa.gov.br/handle/1/16614 |
| _version_ |
1787141315873472512 |
| score |
11.755432 |