# Aboveground Forest Biomass Estimation by the Integration of TLS and ALOS PALSAR Data Using Machine Learning

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

## Abstract

**:**

^{2}value obtained for the RF was 0.94, with an RMSE of 59.72 ton ha

^{−1}for the predicted biomass value. The RMSE% was 15.92, while the RMSE

_{CV}was 0.15. The R

^{2}value for ANN was 0.77, with an RMSE of 98.46 ton ha

^{−1}. The RMSE% was 26.0, while the RMSE

_{CV}was 0.26. RF performed better in estimating the biomass, which ranged from 122.46 to 581.89 ton ha

^{−1}, while uncertainty ranged from 15.75 to 85.14 ton ha

^{−1}. The integration of SAR and LiDAR data using machine learning shows great potential in overcoming AGB saturation of SAR data.

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Study Area

^{2}. The forest type is tropical, moist, deciduous. It is dominated by Shorea robusta (Sal), with co-associated tree species such as Mallotus philippensis (Rohini). The topography of the study area varies from plain to undulating. As the depth of the soil increases, the consistency changes from non-sticky and friable to sticky and firm. A lower horizon of the soil profile is sticky, firm, compact, and comparatively hard [21,22]. The study area is shown in Figure 1.

#### 2.2. Above-Ground Biomass Inventory

#### 2.3. Terrestrial Lidar Data Acquisition and Processing

#### Retrieval of Tree Parameters Using RANSAC Algorithm

- (1)
- D: Dataset with inliers and outliers, which were later characterized and removed using the RANSAC algorithm.
- (2)
- MSS (Minimal Sample Set) of points: These were formed using random mathematical shape parameters out of all the points entered as D, finally yielding a model with definite shape parameters.
- (3)
- k: The points which are required for the MSS.
- (4)
- Theta: Parameters obtained from the MSS points, such as height, radius, center, etc.
- (5)
- CS: The consensus set of points with an error less than the threshold error.
- (6)
- δ: The error threshold, which is responsible for the points that belong to the model or not.

#### 2.4. ALOS PALSAR Data Processing

^{2}+ Q

^{2}. K, keeping absolute calibration constant. ${\sigma}^{0}{}_{i,j},$ Sigma nought at image line and the column “$i,j$” [26]. $G\left({\theta}_{i,j}\right),$ two-way antenna gain at the distributed target look angle corresponding to the pixel at image line and the column “$i,j$”, as shown in Equation (7).

#### Decomposition of Scattering Components

_{surface}, 〈[T]〉

_{double-bounce}, 〈[T]〉

_{volume}, 〈[T]〉

_{helix}, are the coherency matrices for surface, double-bounce, volume, and helix scattering, respectively. The f

_{s}, f

_{d}, f

_{v}, f

_{c}are their respective expansion coefficients. The volume scattering is modeled using the canopy of the tree, which includes the branches and the leaves. The modeled equation can be shown as follows:

_{h}is the horizontal polarization and R

_{v}is the vertical polarization coefficient of Fresnel’s reflection. The double-bounce scattering was obtained from the scattering from the tree trunk and the surface of the ground.

#### 2.5. Prediction of AGB Using RF and ANN

#### 2.6. Mapping Spatial Distribution of AGB

## 3. Results

#### 3.1. Co-Registration of Scans

#### 3.2. TLS-Derived Parameters and Regression Analysis

^{2}, and the height of the trees were retrieved using TLS point cloud. The correlation was established between field-estimated biomass and the TLS-derived parameters. As can be seen in Figure 6, the R

^{2}value obtained between height and biomass was 0.63; the logarithmic relation between height and biomass was also performed to improve the R

^{2}value to 0.88. The R

^{2}value obtained for dbh and biomass was 0.96. This value was enhanced by transforming the value of dbh. The transformation of dbh to dbh

^{2}changes the relation between dbh and biomass, with an R

^{2}value of 0.98.

#### 3.3. ALOS PALSAR L-Band Parameter Retrieval

#### 3.3.1. Yamaguchi Decomposition

^{2}value between double-bounce and biomass was 0.55, while the correlation value obtained for the surface scattering and biomass was 0.05. The R

^{2}value obtained for the volume scattering and biomass was 0.20. Therefore, a better correlation between the double-bounce and biomass can be inferred from the observed data. This seems to correlate with the field data given that the data was acquired in April, which is a leaf off-season in the study area. Thus, the backscatter was mostly from the woody portion of the trees, whereas less backscatter was observed from the canopy of the trees. The decomposition map is shown in Figure 7.

#### 3.3.2. Regression Analysis with Polarimetric Parameters

^{2}value obtained for the CSI and biomass was 0.85, which showed a higher correlation between the canopy and the biomass. The ecosystem comprises more vertical and woody structures. The correlation R

^{2}obtained between VSI and biomass was 0.49, which clearly showed that the thickness of the canopy was less; hence, VSI is less significant in the biomass assessment [30]. The R

^{2}value obtained for BMI and biomass was 0.58 and 0.59 for RVI and biomass. This emphasizes the greater significance of RVI over BMI.

#### 3.3.3. Regression Analysis with Backscatter and Textural Parameters

^{2}value was obtained with entropy and variance. The R

^{2}value for the entropy was 0.21. The R

^{2}value obtained for the variance and biomass was 0.52. The degree of randomness and variability of the area was more relevant, whereas the negative R

^{2}value obtained was for ASM and mean. Therefore, textural parameters such as ASM, entropy, variance, and mean were significant in predicting the biomass of a natural forest.

^{2}value obtained for HH intensity and biomass was 0.40, while 0.49 was obtained for HV intensity. Log transformation was then conducted to enhance the correlation between the variables HH and HV intensity with the biomass. Thus, the R

^{2}value increased to 0.67 and 0.77 for HH and HV intensity with the biomass, respectively.

#### 3.3.4. Regression between ALOS PALSAR L-Band and TLS-Derived Variables

^{2}value of 0.40, while the double-bounce and height were transformed to a higher order to obtain a better correlation with the R

^{2}value of 0.53.

^{2}value of 0.44. A linear relation was found between dbh

^{2}, double-bounce, and the volume-scattering components. The correlation value was enhanced to 0.59 with the high-order polynomial relation for dbh

^{2}and double-bounce, while the dbh

^{2}and volume scattering were log transformed to show some relation, yielding an R

^{2}value of 0.46. Here, the double-bounce showed a better correlation with dbh

^{2}.

#### 3.3.5. Integration of Outputs of ALOS PALSAR and TLS

#### RF Regression Approach

^{2}values, which were 38.95 and 0.94, respectively. Parameters such as ntree and mtry were optimized repeatedly to obtain the best results and reduce errors.

#### ANN Regression Approach

^{2}and RMSE. The negative weight assigned to any variable indicated the least contribution of that variable. The predicted and observed values of biomass are shown in Figure 11. The R

^{2}value obtained for the ANN was 0.77. The number of hidden layers was fitted to ensure maximum accuracy for the prediction. Several hidden layers were tried to ensure minimum RMSE and maximum accuracy for the model. Figure 3 shows the different number of hidden layers and their accuracy at each level. Based on the R

^{2}and RMSE of the model, an analysis was conducted and spatial distribution of biomass was carried out. The R

^{2}value for RF was 0.94, the RMSE was 59.72 ton ha

^{−1}, and the percentage RMSE was 15.97. The R

^{2}value of ANN was 0.77, with an RMSE of 98.46 ton ha

^{−1}and a percentage RMSE of 26.32, as shown in Table 1. Based on this analysis, the RF was found to be the best model for predicting biomass.

#### Spatial Distribution and Uncertainty of Biomass

^{−1}.

^{−1}. The percentage of uncertainty obtained was 20.54%. The uncertainty map of the AGB and biomass spatial distribution is shown in Figure 12.

## 4. Discussion

^{2}value of 0.98 and an RMSE of 0.08 Mg [34]. The collective information obtained from both SAR and LiDAR is key in overcoming the biomass saturation problem in SAR when using machine learning. This is because several machine learning algorithms have already been proven to yield the best results in estimating forest biomass.

## 5. Conclusions

^{2}value of 0.94 and an RMSE of 15.9%. In contrast, the R

^{2}obtained for ANN was 0.77, with an RMSE of 26.3%. It has been concluded that L-band integration with TLS-derived parameters shows great potential for the assessment of forest areas with very high biomass. The uncertainty can be mitigated using different machine learning algorithms and increasing the number of variables to train the model.

## Author Contributions

## Funding

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Houghton, R.A.; Hall, F.; Goetz, S.J. Importance of biomass in the global carbon cycle. J. Geophys. Res. Biogeosci.
**2009**, 114, G00E03. [Google Scholar] [CrossRef] - Brede, B.; Calders, K.; Lau, A.; Raumonen, P.; Bartholomeus, H.M.; Herold, M.; Kooistra, L. Non-destructive tree volume estimation through quantitative structure modelling: Comparing UAV laser scanning with terrestrial LIDAR. Remote Sens. Environ.
**2019**, 233, 111355. [Google Scholar] [CrossRef] - Silva, C.A.; Duncanson, L.; Hancock, S.; Neuenschwander, A.; Thomas, N.; Hofton, M.; Fatoyinbo, L.; Simard, M.; Marshak, C.Z.; Armston, J.; et al. Fusing simulated GEDI, ICESat-2 and NISAR data for regional aboveground biomass mapping. Remote Sens. Environ.
**2021**, 253, 112234. [Google Scholar] [CrossRef] - Kattenborn, T.; Leitloff, J.; Schiefer, F.; Hinz, S. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS J. Photogramm. Remote Sens.
**2021**, 173, 24–49. [Google Scholar] [CrossRef] - Mangla, R.; Kumar, S.; Nandy, S. Random forest regression modelling for forest aboveground biomass estimation using RISAT-1 PolSAR and terrestrial LiDAR data. In Proceedings of the Lidar Remote Sensing for Environmental Monitoring XV, New Delhi, India, 4–7 April 2016; Singh, U.N., Sugimoto, N., Jayaraman, A., Seshasai, M.V.R., Eds.; SPIE: Bellingham, WA, USA, 2016; Volume 9879, p. 98790Q. [Google Scholar]
- Ho Tong Minh, D.; Ndikumana, E.; Vieilledent, G.; McKey, D.; Baghdadi, N. Potential value of combining ALOS PALSAR and Landsat-derived tree cover data for forest biomass retrieval in Madagascar. Remote Sens. Environ.
**2018**, 213, 206–214. [Google Scholar] [CrossRef] - Leonardo, E.M.C.; Watt, M.S.; Pearse, G.D.; Dash, J.P.; Persson, H.J. Comparison of TanDEM-X InSAR data and high-density ALS for the prediction of forest inventory attributes in plantation forests with steep terrain. Remote Sens. Environ.
**2020**, 246, 111833. [Google Scholar] [CrossRef] - Montesano, P.M.; Nelson, R.F.; Dubayah, R.O.; Sun, G.; Cook, B.D.; Ranson, K.J.R.; Næsset, E.; Kharuk, V. The uncertainty of biomass estimates from LiDAR and SAR across a boreal forest structure gradient. Remote Sens. Environ.
**2014**, 154, 398–407. [Google Scholar] [CrossRef] - Peregon, A.; Yamagata, Y. The use of ALOS/PALSAR backscatter to estimate above-ground forest biomass: A case study in Western Siberia. Remote Sens. Environ.
**2013**, 137, 139–146. [Google Scholar] [CrossRef] - Santoro, M.; Wegmüller, U.; Askne, J. Forest stem volume estimation using C-band interferometric SAR coherence data of the ERS-1 mission 3-days repeat-interval phase. Remote Sens. Environ.
**2018**, 216, 684–696. [Google Scholar] [CrossRef] - Kushwaha, S.K.P.; Singh, A.; Jain, K.; Mokros, M. Optimum Number and Positions of Terrestrial Laser Scanner to derive DTM at Forest plot level. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
**2022**, XLIII-B3-2, 457–462. [Google Scholar] [CrossRef] - Liang, X.; Hyyppä, J.; Kaartinen, H.; Lehtomäki, M.; Pyörälä, J.; Pfeifer, N.; Holopainen, M.; Brolly, G.; Francesco, P.; Hackenberg, J.; et al. International benchmarking of terrestrial laser scanning approaches for forest inventories. ISPRS J. Photogramm. Remote Sens.
**2018**, 144, 137–179. [Google Scholar] [CrossRef] - Thapa, R.B.; Watanabe, M.; Motohka, T.; Shimada, M. Potential of high-resolution ALOS-PALSAR mosaic texture for aboveground forest carbon tracking in tropical region. Remote Sens. Environ.
**2015**, 160, 122–133. [Google Scholar] [CrossRef] - Santoro, M.; Cartus, O.; Fransson, J.E.S. Integration of allometric equations in the water cloud model towards an improved retrieval of forest stem volume with L-band SAR data in Sweden. Remote Sens. Environ.
**2021**, 253, 112235. [Google Scholar] [CrossRef] - Stovall, A.E.L.; Shugart, H.H. Improved biomass calibration and validation with terrestrial lidar: Implications for future LiDAR and SAR missions. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2018**, 11, 3527–3537. [Google Scholar] [CrossRef] - Gleason, C.J.; Im, J. Forest biomass estimation from airborne LiDAR data using machine learning approaches. Remote Sens. Environ.
**2012**, 125, 80–91. [Google Scholar] [CrossRef] - Mutanga, O.; Adam, E.; Cho, M.A. High density biomass estimation for wetland vegetation using worldview-2 imagery and random forest regression algorithm. Int. J. Appl. Earth Obs. Geoinf.
**2012**, 18, 399–406. [Google Scholar] [CrossRef] - Powell, S.L.; Cohen, W.B.; Healey, S.P.; Kennedy, R.E.; Moisen, G.G.; Pierce, K.B.; Ohmann, J.L. Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: A comparison of empirical modeling approaches. Remote Sens. Environ.
**2010**, 114, 1053–1068. [Google Scholar] [CrossRef] - Dang, A.T.N.; Nandy, S.; Srinet, R.; Luong, N.V.; Ghosh, S.; Senthil Kumar, A. Forest aboveground biomass estimation using machine learning regression algorithm in Yok Don National Park, Vietnam. Ecol. Inform.
**2019**, 50, 24–32. [Google Scholar] [CrossRef] - Foody, G.M.; Boyd, D.S.; Cutler, M.E.J. Predictive relations of tropical forest biomass from Landsat TM data and their transferability between regions. Remote Sens. Environ.
**2003**, 85, 463–474. [Google Scholar] [CrossRef] - Mukesh; Manhas, R.K.; Tripathi, A.K.; Raina, A.K.; Gupta, M.K.; Kamboj, S.K. Sand and clay mineralogy of sal forest soils of the Doon Siwalik Himalayas. J. Earth Syst. Sci.
**2011**, 120, 123–144. [Google Scholar] [CrossRef] [Green Version] - Watham, T.; Patel, N.R.; Kushwaha, S.P.S.; Dadhwal, V.K.; Kumar, A.S. Evaluation of remote-sensing-based models of gross primary productivity over Indian sal forest using flux tower and MODIS satellite data. Int. J. Remote Sens.
**2017**, 38, 5069–5090. [Google Scholar] [CrossRef] - Singh, A.; Kushwaha, S.K.P.; Nandy, S.; Padalia, H. An approach for tree volume estimation using RANSAC and RHT algorithms from TLS dataset. Appl. Geomat.
**2022**, 14, 785–794. [Google Scholar] [CrossRef] - Singh, A.; Kushwaha, S.K.P.; Nandy, S.; Padalia, H. Novel Approach for Forest allometric eqaution modelling with RANSAC shape detection using Terrestrial Laser Scanner. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
**2022**, XLVIII-4/W, 133–138. [Google Scholar] [CrossRef] - Olofsson, K.; Holmgren, J.; Olsson, H. Tree stem and height measurements using terrestrial laser scanning and the RANSAC algorithm. Remote Sens.
**2014**, 6, 4323–4344. [Google Scholar] [CrossRef] [Green Version] - Rosich, B.; Meadows, P.J.; Monti-Guarnieri, A. ENVISAT ASAR Product Calibration and Product Quality Status. 2004. Available online: https://www.researchgate.net/publication/246078768_ENVISAT_ASAR_Product_Calibration_and_Product_Quality_Status (accessed on 19 December 2022).
- Bergervoet, J.R.; van Campen, P.C.; van der Sanden, W.A.; de Swart, J.J. Phase shift analysis of 0–30 MeV pp scattering data. Phys. Rev. C
**1988**, 38, 15–50. [Google Scholar] [CrossRef] [Green Version] - Yamaguchi, Y.; Moriyama, T.; Ishido, M.; Yamada, H. Four-component scattering model for polarimetric SAR image decomposition. IEEE Trans. Geosci. Remote Sens.
**2005**, 43, 1699–1706. [Google Scholar] [CrossRef] - Haralick, R.M.; Dinstein, I.; Shanmugam, K. Textural Features for Image Classification. IEEE Trans. Syst. Man Cybern.
**1973**, SMC-3, 610–621. [Google Scholar] [CrossRef] [Green Version] - Pope, K.O.; Rey-Benayas, J.M.; Paris, J.F. Radar remote sensing of forest and wetland ecosystems in the Central American tropics. Remote Sens. Environ.
**1994**, 48, 205–219. [Google Scholar] [CrossRef] - Dube, T.; Mutanga, O. Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa. ISPRS J. Photogramm. Remote Sens.
**2015**, 101, 36–46. [Google Scholar] [CrossRef] - Zhao, P.; Lu, D.; Wang, G.; Liu, L.; Li, D.; Zhu, J.; Yu, S. Forest aboveground biomass estimation in Zhejiang Province using the integration of Landsat TM and ALOS PALSAR data. Int. J. Appl. Earth Obs. Geoinf.
**2016**, 53, 1–15. [Google Scholar] [CrossRef] - Bouvet, A.; Mermoz, S.; Le Toan, T.; Villard, L.; Mathieu, R.; Naidoo, L.; Asner, G.P. An above-ground biomass map of African savannahs and woodlands at 25 m resolution derived from ALOS PALSAR. Remote Sens. Environ.
**2018**, 206, 156–173. [Google Scholar] [CrossRef] - Beyene, S.M.; Hussin, Y.A.; Kloosterman, H.E.; Ismail, M.H. Forest Inventory and Aboveground Biomass Estimation with Terrestrial LiDAR in the Tropical Forest of Malaysia. Can. J. Remote Sens.
**2020**, 46, 130–145. [Google Scholar] [CrossRef] - Liao, Z.; He, B.; Quan, X. Potential of texture from SAR tomographic images for forest aboveground biomass estimation. Int. J. Appl. Earth Obs. Geoinf.
**2020**, 88, 102049. [Google Scholar] [CrossRef] - Chowdhury, T.; Thiel, C.; Schmullius, C.; Stelmaszczuk-Górska, M. Polarimetric Parameters for Growing Stock Volume Estimation Using ALOS PALSAR L-Band Data over Siberian Forests. Remote Sens.
**2013**, 5, 5725–5756. [Google Scholar] [CrossRef] [Green Version]

**Figure 1.**Study area [23].

**Figure 3.**Representation of (

**a**) scheme of the plot scanned with TLS and retro-reflectors; (

**b**) scanned plot with the location of reflectors (red dot); (

**c**) extracted plot and single tree; and (

**d**) trunk of the tree with noise, and after the application of a noise filter [23].

**Figure 6.**Correlation plots between TLS-derived parameters and biomass. (

**a**) Correlation between height and biomass; (

**b**) log-transformed correlation between height and biomass; (

**c**) correlation between dbh and biomass; and (

**d**) correlation between dbh

^{2}and biomass.

**Figure 10.**Visualization of (

**a**) % IncMSE and IncNodePurity of the variables used to train the model; (

**b**) out-of-bag (OOB) error while training the data; (

**c**) estimated error based on different no. of trees, (

**d**) error and RMSE of the number of variables and trees in the RF model; and (

**e**) scatterplot for the observed and predicted biomass value (ton/ha).

**Figure 12.**Visualization of the (

**a**) spatial distribution of AGB (t/ha) and (

**b**) uncertainty of AGB (t/ha).

Sr. No. | Model | R^{2} | RMSE (ton ha^{−1}) | RMSE% | RMSE_{CV} |
---|---|---|---|---|---|

1 | RF | 0.94 | 59.72 | 15.97 | 0.15 |

2 | ANN | 0.77 | 98.46 | 26.32 | 0.23 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Singh, A.; Kushwaha, S.K.P.; Nandy, S.; Padalia, H.; Ghosh, S.; Srivastava, A.; Kumari, N.
Aboveground Forest Biomass Estimation by the Integration of TLS and ALOS PALSAR Data Using Machine Learning. *Remote Sens.* **2023**, *15*, 1143.
https://doi.org/10.3390/rs15041143

**AMA Style**

Singh A, Kushwaha SKP, Nandy S, Padalia H, Ghosh S, Srivastava A, Kumari N.
Aboveground Forest Biomass Estimation by the Integration of TLS and ALOS PALSAR Data Using Machine Learning. *Remote Sensing*. 2023; 15(4):1143.
https://doi.org/10.3390/rs15041143

**Chicago/Turabian Style**

Singh, Arunima, Sunni Kanta Prasad Kushwaha, Subrata Nandy, Hitendra Padalia, Surajit Ghosh, Ankur Srivastava, and Nikul Kumari.
2023. "Aboveground Forest Biomass Estimation by the Integration of TLS and ALOS PALSAR Data Using Machine Learning" *Remote Sensing* 15, no. 4: 1143.
https://doi.org/10.3390/rs15041143