ABOVEGROUND BIOMASS ESTIMATION IN A TROPICAL FOREST WITH SELECTIVE LOGGING USING RANDOM FOREST AND LIDAR DATA

The tropical forest is characterized by expressive biomass and stores high amounts of carbon, which is an important variable for climate monitoring. Thus, studies aiming to analyze suitable methods to predict biomass are crucial, especially in the tropics, where dense vegetation makes modeling difficult. Thus, the objective of the present study was to estimate aboveground biomass (AGB) in a tropical forest area with selective logging in the Amazon forest using the Random Forest (RF) machine learning algorithm and LiDAR data. For this, 85 sample units were used at Fazenda Cauaxi, in the municipality of Paragominas, Pará State. LiDAR data were collected in 2014 and made available by the Sustainable Landscapes Project. The software R was used for data analysis. Among the LiDAR metrics, the average height was used as it had the greatest significance to compose the model. The model presented a pseudo R² of 0.69 (value obtained by the RF), Spearman's Correlation Coefficient of 0.80, RMSE of 47.05 Mg.ha-1 (19.84%), and Bias of 2.06 Mg.ha-1 (0.87%). With the results, it was possible to infer that the average height metric was enough to estimate AGB in a tropical forest with selective logging, in addition, the RF algorithm the biomass to be estimated, which can be used to assist in monitoring and action management in areas of selective logging and serve as a basis for climate change mitigation policies.

Download Full-text

Random forest regression modelling for forest aboveground biomass estimation using RISAT-1 PolSAR and terrestrial LiDAR data

10.1117/12.2227380 ◽

2016 ◽

Cited By ~ 2

Author(s):

Rohit Mangla ◽

Shashi Kumar ◽

Subrata Nandy

Keyword(s):

Random Forest ◽

Aboveground Biomass ◽

Biomass Estimation ◽

Lidar Data ◽

Random Forest Regression ◽

Terrestrial Lidar ◽

Regression Modelling ◽

Forest Aboveground Biomass

Download Full-text

Mapping tropical forest biomass with radar and spaceborne LiDAR in Lopé National Park, Gabon: overcoming problems of high biomass and persistent cloud

Biogeosciences ◽

10.5194/bg-9-179-2012 ◽

2012 ◽

Vol 9 (1) ◽

pp. 179-191 ◽

Cited By ~ 108

Author(s):

E. T. A. Mitchard ◽

S. S. Saatchi ◽

L. J. T. White ◽

K. A. Abernethy ◽

K. J. Jeffery ◽

...

Keyword(s):

Tropical Forest ◽

Aboveground Biomass ◽

National Park ◽

Radar Data ◽

Optical Data ◽

Biomass Estimation ◽

Lidar Data ◽

High Biomass ◽

Alos Palsar ◽

Lope National Park

Abstract. Spatially-explicit maps of aboveground biomass are essential for calculating the losses and gains in forest carbon at a regional to national level. The production of such maps across wide areas will become increasingly necessary as international efforts to protect primary forests, such as the REDD+ (Reducing Emissions from Deforestation and forest Degradation) mechanism, come into effect, alongside their use for management and research more generally. However, mapping biomass over high-biomass tropical forest is challenging as (1) direct regressions with optical and radar data saturate, (2) much of the tropics is persistently cloud-covered, reducing the availability of optical data, (3) many regions include steep topography, making the use of radar data complex, (5) while LiDAR data does not suffer from saturation, expensive aircraft-derived data are necessary for complete coverage. We present a solution to the problems, using a combination of terrain-corrected L-band radar data (ALOS PALSAR), spaceborne LiDAR data (ICESat GLAS) and ground-based data. We map Gabon's Lopé National Park (5000 km2) because it includes a range of vegetation types from savanna to closed-canopy tropical forest, is topographically complex, has no recent contiguous cloud-free high-resolution optical data, and the dense forest is above the saturation point for radar. Our 100 m resolution biomass map is derived from fusing spaceborne LiDAR (7142 ICESat GLAS footprints), 96 ground-based plots (average size 0.8 ha) and an unsupervised classification of terrain-corrected ALOS PALSAR radar data, from which we derive the aboveground biomass stocks of the park to be 78 Tg C (173 Mg C ha−1). This value is consistent with our field data average of 181 Mg C ha−1, from the field plots measured in 2009 covering a total of 78 ha, and which are independent as they were not used for the GLAS-biomass estimation. We estimate an uncertainty of &pm;25% on our carbon stock value for the park. This error term includes uncertainties resulting from the use of a generic tropical allometric equation, the use of GLAS data to estimate Lorey's height, and the necessity of separating the landscape into distinct classes. As there is currently no spaceborne LiDAR satellite in operation (GLAS data is available for 2003–2009 only), this methodology is not suitable for change-detection. This research underlines the need for new satellite LiDAR data to provide the potential for biomass-change estimates, although this need will not be met before 2015.

Download Full-text

Mapping tropical forest biomass with radar and spaceborne LiDAR: overcoming problems of high biomass and persistent cloud

Biogeosciences Discussions ◽

10.5194/bgd-8-8781-2011 ◽

2011 ◽

Vol 8 (4) ◽

pp. 8781-8815 ◽

Cited By ~ 12

Author(s):

E. T. A. Mitchard ◽

S. S. Saatchi ◽

L. J. T. White ◽

K. A. Abernethy ◽

K. J. Jeffery ◽

...

Keyword(s):

Tropical Forest ◽

Aboveground Biomass ◽

Degradation Mechanism ◽

National Level ◽

Radar Data ◽

Optical Data ◽

Biomass Estimation ◽

Lidar Data ◽

High Biomass ◽

Alos Palsar

Abstract. Spatially-explicit maps of aboveground biomass are essential for calculating the losses and gains in forest carbon at a regional to national level. The production of such maps across wide areas will become increasingly necessary as international efforts to protect primary forests, such as the REDD+ (Reducing Emissions from Deforestation and forest Degradation) mechanism, come into effect, alongside their use for management and research more generally. However, mapping biomass over high-biomass tropical forest is challenging as (1) direct regressions with optical and radar data saturate, (2) much of the tropics is persistently cloud-covered, reducing the availability of optical data, (3) many regions include steep topography, making the use of radar data complex, (4) while LiDAR data does not suffer from saturation, expensive aircraft-derived data are necessary for complete coverage. We present a solution to the problems, using a combination of terrain-corrected L-band radar data (ALOS PALSAR), spaceborne LiDAR data (ICESat GLAS) and ground-based data. We map Gabon's Lopé National Park (5000 km2) because it includes a range of vegetation types from savanna to closed-canopy tropical forest, is topographically complex, has no recent cloud-free high-resolution optical data, and the dense forest is above the saturation point for radar. Our 100 m resolution biomass map is derived from fusing spaceborne LiDAR (7142 ICESat GLAS footprints), 96 ground-based plots (average size 0.8 ha) and an unsupervised classification of terrain-corrected ALOS PALSAR radar data, from which we derive the aboveground biomass stocks of the park to be 78 Tg C (173 Mg C ha−1). This value is consistent with our field data average of 181 Mg C ha−1, from the field plots measured in 2009 covering a total of 78 ha, and which are independent as they were not used for the GLAS-biomass estimation. We estimate an uncertainty of ± 25 % on our carbon stock value for the park. This error term includes uncertainties resulting from the use of a generic tropical allometric equation, the use of GLAS data to estimate Lorey's height, and the necessity of separating the landscape into distinct classes. As there is currently no spaceborne LiDAR satellite in operation (GLAS data is available for 2003–2007 only), this methodology is not suitable for change-detection. This research underlines the need for new satellite LiDAR data to provide the potential for biomass-change estimates, although this need will not be met before 2015.

Download Full-text

Comparison of Statistical Modelling Approaches for Estimating Tropical Forest Aboveground Biomass Stock and Reporting Their Changes in Low-Intensity Logging Areas Using Multi-Temporal LiDAR Data

Remote Sensing ◽

10.3390/rs12091498 ◽

2020 ◽

Vol 12 (9) ◽

pp. 1498 ◽

Cited By ~ 4

Author(s):

Franciel Eduardo Rex ◽

Carlos Alberto Silva ◽

Ana Paula Dalla Corte ◽

Carine Klauberg ◽

Midhun Mohan ◽

...

Keyword(s):

Tropical Forest ◽

Aboveground Biomass ◽

Ordinary Least Squares ◽

Forest Growth ◽

Selective Logging ◽

Airborne Lidar ◽

Support Vector ◽

Lidar Data ◽

Field Plots ◽

Forest Aboveground Biomass

Accurately quantifying forest aboveground biomass (AGB) is one of the most significant challenges in remote sensing, and is critical for understanding global carbon sequestration. Here, we evaluate the effectiveness of airborne LiDAR (Light Detection and Ranging) for monitoring AGB stocks and change (ΔAGB) in a selectively logged tropical forest in eastern Amazonia. Specifically, we compare results from a suite of different modelling methods with extensive field data. The calibration AGB values were derived from 85 square field plots sized 50 × 50 m field plots established in 2014 and which were estimated using airborne LiDAR data acquired in 2012, 2014, and 2017. LiDAR-derived metrics were selected based upon Principal Component Analysis (PCA) and used to estimate AGB stock and change. The statistical approaches were: ordinary least squares regression (OLS), and nine machine learning approaches: random forest (RF), several variations of k-nearest neighbour (k-NN), support vector machine (SVM), and artificial neural networks (ANN). Leave-one-out cross-validation (LOOCV) was used to compare performance based upon root mean square error (RMSE) and mean difference (MD). The results show that OLS had the best performance with an RMSE of 46.94 Mg/ha (19.7%) and R² = 0.70. RF, SVM, and ANN were adequate, and all approaches showed RMSE ≤54.48 Mg/ha (22.89%). Models derived from k-NN variations all showed RMSE ≥64.61 Mg/ha (27.09%). The OLS model was thus selected to map AGB across the time-series. The mean (±sd—standard deviation) predicted AGB stock at the landscape level was 229.10 (±232.13) Mg/ha in 2012, 258.18 (±106.53) in 2014, and 240.34 (sd ± 177.00) Mg/ha in 2017, showing the effect of forest growth in the first period and logging in the second period. In most cases, unlogged areas showed higher AGB stocks than logged areas. Our methods showed an increase in AGB in unlogged areas and detected small changes from reduced-impact logging (RIL) activities occurring after 2012. We also detected that the AGB increase in areas logged before 2012 was higher than in unlogged areas. Based on our findings, we expect our study could serve as a basis for programs such as REDD+ and assist in detecting and understanding AGB changes caused by selective logging activities in tropical forests.

Download Full-text

EFFECTS OF SELECTIVE LOGGING ON CARBON DYNAMICS: VARIATION IN ABOVEGROUND BIOMASS AND SOIL RESPIRATION IN PRE- AND POST-LOGGING FOREST STANDS OF A MOIST TROPICAL FOREST IN GHANA

10.37099/mtu.dc.etdr/329 ◽

2017 ◽

Author(s):

Akwasi Duah-Gyamfi

Keyword(s):

Soil Respiration ◽

Tropical Forest ◽

Aboveground Biomass ◽

Carbon Dynamics ◽

Selective Logging ◽

Forest Stands

Download Full-text

Aboveground Biomass Estimation Using Structure from Motion Approach with Aerial Photographs in a Seasonal Tropical Forest

Forests ◽

10.3390/f6113882 ◽

2015 ◽

Vol 6 (12) ◽

pp. 3882-3898 ◽

Cited By ~ 54

Author(s):

Tetsuji Ota ◽

Miyuki Ogawa ◽

Katsuto Shimizu ◽

Tsuyoshi Kajisa ◽

Nobuya Mizoue ◽

...

Keyword(s):

Tropical Forest ◽

Structure From Motion ◽

Aboveground Biomass ◽

Aerial Photographs ◽

Biomass Estimation

Download Full-text

Aboveground-Biomass Estimation of a Complex Tropical Forest in India Using Lidar

Remote Sensing ◽

10.3390/rs70810607 ◽

2015 ◽

Vol 7 (8) ◽

pp. 10607-10625 ◽

Cited By ~ 14

Author(s):

Cédric Véga ◽

Udayalakshmi Vepakomma ◽

Jules Morel ◽

Jean-Luc Bader ◽

Gopalakrishnan Rajashekar ◽

...

Keyword(s):

Tropical Forest ◽

Aboveground Biomass ◽

Biomass Estimation

Download Full-text

Stratification-Based Forest Aboveground Biomass Estimation in a Subtropical Region Using Airborne Lidar Data

Remote Sensing ◽

10.3390/rs12071101 ◽

2020 ◽

Vol 12 (7) ◽

pp. 1101 ◽

Cited By ~ 2

Author(s):

Xiandie Jiang ◽

Guiying Li ◽

Dengsheng Lu ◽

Erxue Chen ◽

Xinliang Wei

Keyword(s):

Aboveground Biomass ◽

Forest Type ◽

Forest Stand ◽

Airborne Lidar ◽

Accurate Estimation ◽

Biomass Estimation ◽

Lidar Data ◽

Forest Types ◽

Estimation Model ◽

Forest Aboveground Biomass

Species-rich subtropical forests have high carbon sequestration capacity and play important roles in regional and global carbon regulation and climate changes. A timely investigation of the spatial distribution characteristics of subtropical forest aboveground biomass (AGB) is essential to assess forest carbon stocks. Lidar (light detection and ranging) is regarded as the most reliable data source for accurate estimation of forest AGB. However, previous studies that have used lidar data have often beenbased on a single model developed from the relationships between lidar-derived variables and AGB, ignoring the variability of this relationship in different forest types. Although stratification of forest types has been proven to be effective for improving AGB estimation, how to stratify forest types and how many strata to use are still unclear. This research aims to improve forest AGB estimation through exploring suitable stratification approaches based on lidar and field survey data. Different stratification schemes including non-stratification and stratifications based on forest types and forest stand structures were examined. The AGB estimation models were developed using linear regression (LR) and random forest (RF) approaches. The results indicate the following: (1) Proper stratifications improved AGB estimation and reduced the effect of under- and overestimation problems; (2) the finer forest type strata generated higher accuracy of AGB estimation but required many more sample plots, which were often unavailable; (3) AGB estimation based on stratification of forest stand structures was similar to that based on five forest types, implying that proper stratification reduces the number of sample plots needed; (4) the optimal AGB estimation model and stratification scheme varied, depending on forest types; and (5) the RF algorithm provided better AGB estimation for non-stratification than the LR algorithm, but the LR approach provided better estimation with stratification. Results from this research provide new insights on how to properly conduct forest stratification for AGB estimation modeling, which is especially valuable in tropical and subtropical regions with complex forest types.

Download Full-text