Forest Aboveground Biomass Estimation Research Articles

Estimating Forest Aboveground Biomass Using a Combination of Geographical Random Forest and Empirical Bayesian Kriging Models

Accurately estimating forest aboveground biomass (AGB) is imperative for comprehending carbon cycling, calculating carbon budgets, and formulating sustainable forest management plans. Currently, random forest (RF) and other machine learning models are widely used to estimate forest AGB, as they can effectively handle nonlinear relationships. However, by constructing a global model using all the samples collected from a study area, these models fail to account for the spatial heterogeneity in the AGB and cannot correct the prediction biases, thereby constraining the estimation accuracy. To overcome these limitations, we proposed a novel approach termed geographical random forest and empirical Bayesian kriging (GRFEBK). This hybrid model combines the localized modeling capability of geographical random forest (GRF) with the bias correction strength of empirical Bayesian kriging (EBK). GRF adapts RF to account for the spatial heterogeneity of the AGB, while EBK utilizes the spatial autocorrelation of residuals to correct the prediction deviations. This study was conducted in Hainan Island, utilizing spectral bands, vegetation indices, tasseled cap components derived from Landsat-8 imagery, backscattering coefficients from ALOS-2 synthetic aperture radar, topographic features, and the forest canopy height as the explanatory variables. A total of 195 forest aboveground biomass (AGB) samples were collected for modeling and assessing the predictive accuracy. The results demonstrate that, among the tested models, including GRFEBK, RF, support vector machine (SVM), k-nearest neighbor (KNN), geographically weighted regression (GWR), GRF, and EBK, GRFEBK attains the highest R2 (0.78) and the lowest RMSE (36.04 Mg/ha) and RRMSE (22.87%), significantly outperforming the conventional models and using GRF or EBK alone. These results demonstrate that by accounting for local non-stationarity in AGB and correcting prediction biases, GRFEBK achieves significantly higher accuracy than conventional RF and other models. While the results are promising, the computational cost of GRFEBK and its performance under varying geographical conditions warrant further investigation at larger scales to assess its broader applicability. Nevertheless, GRFEBK provides an innovative and more reliable approach for accurate forest AGB estimation with great potential to support global forest resource monitoring.

Interacting Sentinel-2A, Sentinel 1A, and GF-2 Imagery to Improve the Accuracy of Forest Aboveground Biomass Estimation in a Dry-Hot Valley

Carbon absorption and storage in forests is one of the important ways to mitigate climate change. Therefore, it is essential to use a variety of remote-sensing resources to accurately estimate forest aboveground biomass (AGB) in dry-hot valley regions. In this study, satellite images from the Sentinel-1A, Sentinel-2A, and Gaofen-2 satellites were utilized to estimate the forest AGB in Yuanmou County, Yunnan Province, China. Different combinations of image data, based on selected variables of stepwise regression and their performance in constructing linear stepwise regression (LSR) and random forest (RF) models, were explored. The results showed that: (1) after adding the polarized values of the synthetic aperture radar backscatter coefficients, the combination fitting effect was significantly improved; (2) the fitting effect of the Sentinel-1A + Sentinel-2A + Gaofen-2 data combination was superior to the other combinations, indicating that the effective extraction of forest horizon and vertical information can improve the estimation effect of the forest AGB; and (3) the RF model exhibited superior fitting performance compared to the LSR model across all permutations of remotely sensed image datasets, with R2 values of 0.71 and 0.65, and RMSE values of 30.67 and 33.79 Mg/ha, respectively. These findings lay the groundwork for enhancing the precision of AGB estimation in dry-hot valley areas by integrating Sentinel-2A, Sentinel-1A, and GF-2 imagery, providing valuable insights for future research and applications.

A Multi-Scale Forest Above-Ground Biomass Mapping Approach: Employing a Step-by-Step Spatial Downscaling Method with Bias-Corrected Ensemble Machine Learning

The accurate estimation of forest above-ground biomass (AGB) is vital for monitoring changes in forest carbon sinks. However, the spatial heterogeneity of AGB, coupled with inherent uncertainties, poses challenges in acquiring high-quality AGBs. This study introduced a bias-corrected ensemble machine learning (ML) algorithm for AGB downscaling that integrated a ML for AGB mapping with another for residual mapping. The accuracies of six bias-corrected ensemble ML algorithms were evaluated at resolutions of 0.05°, 0.025°, and 0.01°. Moreover, a step-by-step downscaling (SBSD) method was introduced, utilizing bias-corrected ensemble ML algorithms to downscale AGB from 0.1° to 0.05°, 0.025°, and 0.01° resolutions and was compared with the direct downscaling (DD) at three scales. A comparative analysis was conducted in the Daxing’anling Mountains and Xiaoxing’anling Mountains. AGB and corresponding uncertainty maps at three scales were generated using SBSD. The results showed that the efficacy of the XGBoost-based AGB model combined with the random forest-based residual correction model was superior. Spatial patterns in AGB maps generated by SBSD and DD were found to be similar. Notably, SBSD yielded enhanced accuracy in the Daxing’anling Mountains with complex topography, while both performed comparably in the Xiaoxing’anling Mountains with milder topography, highlighting SBSD’s advantages in high heterogeneity areas.

Forest Aboveground Biomass Estimation Using Multisource Remote Sensing Data and Deep Learning Algorithms: A Case Study over Hangzhou Area in China

The accurate estimation of forest aboveground biomass is of great significance for forest management and carbon balance monitoring. Remote sensing instruments have been widely applied in forest parameters inversion with wide coverage and high spatiotemporal resolution. In this paper, the capability of different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 and Landsat-8) and various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), in aboveground forest biomass estimation. In particular, based on the forest inventory data of Hangzhou in China, the Random Forest (RF), Convolutional Neural Network (CNN) and Convolutional Neural Networks Long Short-Term Memory Networks (CNN-LSTM) algorithms were deployed to construct the forest biomass estimation models, respectively. The estimate accuracies were evaluated under the different configurations of images and methods. The results show that for the SAR data, ALOS-2 has a higher biomass estimation accuracy than the GaoFen-3 and Sentinel-1. Moreover, the GaoFen-6 data is slightly worse than Sentinel-2 and Landsat-8 optical data in biomass estimation. In contrast with the single source, integrating multisource data can effectively enhance accuracy, with improvements ranging from 5% to 10%. The CNN-LSTM generally performs better than CNN and RF, regardless of the data used. The combination of CNN-LSTM and multisource data provided the best results in this case and can achieve the maximum R2 value of up to 0.74. It was found that the majority of the biomass values in the study area in 2018 ranged from 60 to 90 Mg/ha, with an average value of 64.20 Mg/ha.

Influence of BRDF Models and Solar Zenith Angles on Forest Above-Ground Biomass Derived from MODIS Multi-Angular Indices

Multi-angular remote sensing observation contains crucial information on forest structure parameters. Here, our goal is to examine the ability of multi-angular indices, which are constructed by the typical-angular reflectances in red and NIR bands from MODIS observations, for the retrieval of forest biomass based on the field-measured above-ground biomass (AGB) data. Specifically, we employed the updated version of the MCD43A1 BRDF parameter product as an input for BRDF models to reconstruct the MODIS typical-angular reflectances. Furthermore, we evaluated the effects of different configurations of BRDF models and solar zenith angles (SZA) on forest AGB estimation using our developed multi-angular indices. The semivariogram analysis strategy combined with Landsat ground-surface reflectance data was employed to determine the MODIS pixel heterogeneity; the survey data from field sites of homogeneous pixels was used in our analysis and validation. The results show that our developed multi-angular indices based on a hot-revised BRDF model, under a SZA of 45°, when combined with forest cover information, can account for up to 72% of the variation forest AGB, with an RMSE = 45 Mg/ha. We also found that different kernels for the BRDF models influenced the weight parameters of the biomass inversion equation but did not significantly affect the estimated AGB. In conclusion, our method can enable the better usage of MODIS multi-angular observations for forest AGB estimation.

High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms

Accurately estimating the above-ground biomass (AGB) of high-density tropical rainforests is a challenging issue. In this study, airborne multi-baseline PolInSAR data were used to estimate the tropical rainforest AGB in Gabon, Africa. The most suitable baseline combination of the PolInSAR data was initially determined through baseline selection, and the PolInSAR parameters related to forest height were obtained based on the forest canopy height estimation theory and microwave penetration depth theory. The height parameter, baseline parameter, and observation geometry parameter were then used as independent variables to construct the AGB regression model. Support vector regression (SVR) was chosen as the AGB estimation model, and the global best particle swarm algorithm (GLB-PSO) was used to optimize the SVR model’s parameters. The results show that the RFECV variable selection method is superior to the Pearson method. The GLB-PSO algorithm can also further improve the saturation point of the SVR model—the estimation results show that the saturation point of AGB estimation of PolInSAR multidimensional features combined with the SVR machine learning algorithm is up to 500 Mg/ha, while this saturation point can be increased to 650 Mg/ha when using the GLB-PSO-SVR algorithm.

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

The estimation of forest above-ground biomass (AGB) can be significantly improved by leveraging remote sensing (RS) and deep learning (DL) techniques. In this process, it is crucial to obtain appropriate RS features and develop a suitable model. However, traditional methods such as random forest (RF) feature selection often fail to adequately consider the complex relationships within high-dimensional RS feature spaces. Moreover, challenges related to parameter selection and overfitting inherent in DL models may compromise the accuracy of AGB estimation. Therefore, this study proposes a novel framework based on freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 optical data. Firstly, we designed new indices through the formula analogous with vegetation index calculation to integrate multidimensional spectral and structural information. Then, leveraging the simplicity of computational principles, a pigeon-inspired optimization algorithm (PIO) was introduced into a bi-directional long short-term memory neural network (PIO-BiLSTM), which achieved the set objective function through repeated iteration and validation to obtain the optimal model parameters. Finally, to verify the framework’s effect, we conducted experiments in two different tree species and compared another seven classical optimization algorithms and machine learning models. The results indicated that the new indices significantly improved the inversion accuracy of all models in both categories, and the PIO-BiLSTM model achieved the highest accuracy (Category-1: R2 = 0.8055, MAE = 8.8475 Mg·ha−1, RMSE = 12.2876 Mg·ha−1, relative RMSE = 18.1715%; Category-2: R2 = 0.7956, MAE = 1.7103 Mg·ha−1, RMSE = 2.2887 Mg·ha−1, relative RMSE = 9.3000%). Compared with existing methods, the proposed framework greatly reduced the labor costs in parameter selection, and its potential uncertainty also decreased by up to 9.0%. Furthermore, the proposed method has a strong generalization ability and is independent of tree species, indicating its great potential for future forest AGB inversion in wider regions with diverse forest types.

UAV-LiDAR Integration with Sentinel-2 Enhances Precision in AGB Estimation for Bamboo Forests

Moso bamboo forests, recognized as a distinctive and significant forest resource in subtropical China, contribute substantially to efficient carbon sequestration. The accurate assessment of the aboveground biomass (AGB) in Moso bamboo forests is crucial for evaluating their impact on the carbon balance within forest ecosystems at a regional scale. In this study, we focused on the Moso bamboo forest located in Shanchuan Township, Zhejiang Province, China. The primary objective was to utilize various data sources, namely UAV-LiDAR (UL), Sentinel-2 (ST), and a combination of UAV-LiDAR with Sentinel-2 (UL + ST). Employing the Boruta algorithm, we carefully selected characterization variables for analysis. Our investigation delved into establishing correlations between UAV-LiDAR characterization parameters, Sentinel-2 feature parameters, and the aboveground biomass (AGB) of the Moso bamboo forest. Ground survey data on Moso bamboo forest biomass served as the basis for our analysis. To enhance the accuracy of AGB estimation in the Moso bamboo forest, we employed three distinct modeling techniques: multivariate linear regression (MLR), support vector regression (SVR), and random forest (RF). Through this approach, we aimed to compare the impact of different data sources and modeling methods on the precision of AGB estimation in the studied bamboo forest. This study revealed that (1) the point cloud intensity of UL, the variables of canopy cover (CC), gap fraction (GF), and leaf area index (LAI) reflect the structure of Moso bamboo forests, and the variables indicating the height of the forest stand (AIH1, AIHiq, and Hiq) had a significant effect on the AGB of Moso bamboo forests, significantly impact Moso bamboo forest AGB. Vegetation indices such as DVI and SAVI in ST also exert a considerable effect on Moso bamboo forest AGB. (2) AGB estimation models constructed based on UL consistently demonstrated higher accuracy compared with ST, achieving R2 values exceeding 0.7. Regardless of the model used, UL consistently delivered superior accuracy in Moso bamboo forest AGB estimation, with RF achieving the highest precision at R2 = 0.88. (3) Integration of ST with UL substantially improved the accuracy of AGB estimation for Moso bamboo forests across all three models. Specifically, using RF, the accuracy of AGB estimation increased by 97.7%, with R2 reaching 0.89 and RMSE reduced by 124.4%. As a result, the incorporation of LiDAR data, which reflects the stand structure, has proven to enhance the accuracy of aboveground biomass (AGB) estimation in Moso bamboo forests when combined with multispectral remote sensing data. This integration serves as an effective solution to address the limitations of single optical remote sensing methods, which often suffer from signal saturation, leading to lower accuracy in estimating Moso bamboo forest biomass. This approach offers a novel perspective and opens up new possibilities for improving the precision of Moso bamboo forest biomass estimation through the utilization of multiple remote sensing sources.

Assessing the effect of ensemble learning algorithms and validation approach on estimating forest aboveground biomass: a case study of natural secondary forest in Northeast China

ABSTRACT Accurate estimation of forest aboveground biomass is essential for the assessment of regional carbon cycle and the climate change in the terrestrial ecosystem. Currently, ensemble learning algorithms and cross-validation methods have been widely applied to estimate regional forest Above Ground Biomass (AGB). However, the effects of ensemble learning algorithms, validation methods, and their interactions on forest AGB estimation were rarely investigated. Based on Landsat 8 Operational Land Imager (OLI) imagery, Airborne Laser Scanning (ALS) data and China’s National Forest Continuous Inventory data, this study explored the effects of five ensemble learning algorithms, including Simple Averaging (SA), Weighted Averaging (WA), Stacked Generalization (SG), Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and two validation approaches (i.e. 10-fold and leave-one-out cross-validation) on the AGB estimation of the Natural Secondary Forests (NSFs) in northeast China. The results revealed that the ensemble learning algorithms that combine heterogenous-based models (i.e. SA, WA, SG) generally produced higher accuracy than the base models (i.e. Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Convolutional Neural Network (CNN)). Among all ensemble learning algorithms, the SG algorithm has the highest accuracy whereas the XGBoost algorithm has the lowest accuracy. Although prediction models considerably impact the accuracy of AGB estimation, the validation approach also plays a non-negligible role in AGB estimation. The leave-one-out cross-validation produced much higher accuracy than the 10-fold cross-validation using the same prediction model and tends to generate over-optimistic AGB estimates compared to 10-fold cross-validation, especially for the averaging and stacking ensemble learning algorithms (i.e. SA, WA, SG). This study highlights the potential challenges of applying a leave-one-out cross-validation approach and provides a scientific foundation for the feasibility of different ensemble learning algorithms and cross-validation approaches for accurate AGB estimation.

Estimation of Above-Ground Forest Biomass in Nepal by the Use of Airborne LiDAR, and Forest Inventory Data

Forests play a significant role in sequestering carbon and regulating the global carbon and energy cycles. Accurately estimating forest biomass is crucial for understanding carbon stock and sequestration, forest degradation, and climate change mitigation. This study was conducted to estimate above-ground biomass (AGB) and compare the accuracy of the AGB estimating models using LiDAR (light detection and ranging) data and forest inventory data in the central Terai region of Nepal. Airborne LiDAR data were collected in 2021 and made available by Nepal Ban Nigam Limited, Government of Nepal. Thirty-two metrics derived from the laser-scanned LiDAR point cloud data were used as predictor variables (independent variables), while the AGB calculated from field data at the plot level served as the response variable (dependent variable). The predictor variables in this study were LiDAR-based height and canopy metrics. Two statistical methods, the stepwise linear regression (LR) and the random forest (RF) models, were used to estimate forest AGB. The output was an accurate map of AGB for each model. The RF method demonstrated better precision compared to the stepwise LR model, as the R2 metric increased from 0.65 to 0.85, while the RMSE values decreased correspondingly from 105.88 to 60.9 ton/ha. The estimated AGB density varies from 0 to 446 ton/ha among the sample plots. This study revealed that the height-based LiDAR metrics, such as height percentile or maximum height, can accurately and precisely predict AGB quantities in tropical forests. Consequently, we confidently assert that substantial potential exists to monitor AGB levels in forests effectively by employing airborne LiDAR technology in combination with field inventory data.

Forest aboveground biomass estimation by GEDI and multi-source EO data fusion over Indian forest

ABSTRACT Monitoring changes in carbon stocks through forest biomass assessment is crucial for carbon cycle studies. However, challenges in obtaining timely and reliable ground measurements hinder creation of the spatially continuous maps of forest aboveground biomass density (AGBD). This study proposes an approach for generating spatially continuous maps of forest aboveground biomass density (AGBD) by combining Global Ecosystem Dynamics Investigation (GEDI) LiDAR-based data with open-access earth observation (EO) data. The key contribution of the study lies in the systematic evaluation of various model configurations to select the optimal model for AGBD generation. The evaluation considered various model configurations, including predictor sets, spatial resolution, beam selection, and sensitivity thresholds. We used a Random Forest model, trained through five-fold cross-validation on 80% of the total data, to estimate AGBD in the Indian forest region. Model performance was assessed using the 20% independent test dataset. Results, using Sentinel-1 and 2 predictors, yielded R2 values of 0.55 to 0.60 and RMSE of 48.5 to 56.3 Mg/ha. Incorporating forest and agroclimatic zone attributes improved performance (R2: 0.59 to 0.69, RMSE: 42.2 to 53.3 Mg/ha). The selection of the top 15 predictors, which favoured features from Sentinel-2, DEM, forest attributes, and agroclimatic zones, and GEDI data with sensitivity >0.98, yielded the optimal model with an R2 of 0.64 and RMSE of 46.59 Mg/ha. The results underscore the significance of incorporating attributes like forest and agro-climatic zones and the need for an optimal model selection considering predictor types and GEDI shot characteristics. The top-performing model is validated in Simdega, Jharkhand (R2: 0.74, RMSE: 39.3 Mg/ha), demonstrating the methodological potential of this approach. Overall, this study emphasizes the methodological prospects of integrating multi-source open-access EO data to produce spatially continuous aboveground biomass (AGB) maps through data fusion.

Improved random forest algorithms for increasing the accuracy of forest aboveground biomass estimation using Sentinel-2 imagery

A simpler, unbiased, and comprehensive random forest (RF) model is needed to improve the accuracy of aboveground biomass (AGB) estimation. In this study, data were obtained from 128 sample plots of Pinus yunnanensis forest located in Chuxiong prefecture, Yunnan province, China. Sentinel-2 imagery data were applied to extract the important predictors of forest AGB, which were screened using the Boruta algorithm. We compared the fitting performance of two modified random forest models − regularized random forest (RRF) and quantile random forest (QRF) − with the random forest model. Moreover, we combined the smallest mean error of each quantile model as the best QRF (QRFb). The result showed: (1) Window sizes of 3 × 3 pixels and 5 × 5 pixels demonstrated greater sensitivity and suitability for estimating AGB than the 7 × 7 pixels window size. Enhanced vegetation indices derived from Red Edge 1 (B5) and Near-Infrared bands (B8A) were strongly correlated with AGB, indicating the heightened sensitivity of B5 and B8A bands to biomass and their potential in AGB estimation. (2) The RRF model outperformed both the standard RF and QRF in fitting performance, with an R2 of 0.56 and RMSE 57.14 Mg/ha. (3) The QRFb model exhibited the highest R2 of 0.88 and lowest RMSE of 29.56 Mg/ha, significantly reducing overestimation and underestimation issues. The modified RF regression supplies new insights into improving forest AGB estimation, which will be helpful for future research addressing carbon cycling.

A comparative study on the efficacy of dual-pol and full-pol ASAR data in radiative transfer modeling for forest above-ground biomass estimation

ABSTRACT In this study, a comprehensive evaluation of the potential of dual-polarization and full-polarization L- and S-band airborne SAR (LS-ASAR) data (ISRO’s dual-frequency airborne SAR mounted on NASA’s Gulfstream III aircraft) in forest above-ground biomass (AGB) estimation has been carried out. The study area comprises the temperate forests of the Lenoir landing site in Southwest Alabama, United States of America. A trunk scattering model based on Vector Radiative Transfer (VRT) theory is used in this study to estimate the AGB. Full-polarization ASAR data inversion retrieves three critical biophysical parameters: tree height, diameter at breast height (DBH), and tree count, whereas with dual-polarization ASAR data, the model is limited to retrieving only two parameters (tree height and DBH). These parameters are then employed in a suitable allometric equation to estimate the AGB over the study area. Validation of the retrieval results is performed through comparison with ground-truth measurements taken from the study site. The findings demonstrate that the inversion of L-band full-polarized data yields the highest correlation (R2 = 0.87, RMSE = 20.37 t/ha), revealing high accuracy in AGB estimation. The L-band dual-polarized data shows a high correlation (R2 = 0.83, RMSE = 30.66 t/ha), indicating reasonable accuracy. However, the S-band data, both full and dual-polarized, reveals weaker correlations with higher RMSE values (R2 = 0.59, RMSE = 55.07 t/ha, and R2 = 0.49, RMSE = 58.31 t/ha, respectively), suggesting a lower degree of reliability. This study emphasizes the pre-eminence of L-band fully polarized data inversion for reliable and accurate AGB estimation while also showing the utility of relatively ubiquitous dual-pol data (L-band) to achieve reasonable accuracy for the same.

Estimation of Aboveground Biomass for Different Forest Types Using Data from Sentinel-1, Sentinel-2, ALOS PALSAR-2, and GEDI

Forest aboveground biomass (AGB) is integral to the global carbon cycle and climate change study. Local and regional AGB mapping is crucial for understanding global carbon stock dynamics. NASA’s global ecosystem dynamics investigation (GEDI) and combination of multi-source optical and synthetic aperture radar (SAR) datasets have great potential for local and regional AGB estimation and mapping. In this study, GEDI L4A AGB data and ground sample plots worked as true AGB values to explore their difference for estimating forest AGB using Sentinel-1 (S1), Sentinel-2 (S2), and ALOS PALSAR-2 (PALSAR) data, individually and in their different combinations. The effects of forest types and different true AGB values for validation were investigated in this study, as well. The combination of S1 and S2 performed best in forest AGB estimation with R2 ranging from 0.79 to 0.84 and RMSE ranging from 7.97 to 29.42 Mg/ha, with the ground sample plots used as ground truth data. While for GEDI L4A AGB product working as reference, R2 values range from 0.36 to 0.47 and RMSE values range from 31.41 to 37.50 Mg/ha. The difference between using GEDI L4A and ground sample plot as reference shows obvious dependence on forest types. In summary, optical dataset and its combination with SAR performed better in forest AGB estimation when the average AGB is less than 150 Mg/ha. The AGB predictions from GEDI L4A AGB product used as reference underperformed across the different forest types and study sites. However, GEDI can work as ground truth data source for forest AGB estimation in a certain level of estimation accuracy.

Deep point cloud regression for above-ground forest biomass estimation from airborne LiDAR

Quantifying forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures by aiding local forest management, studying processes driving af-, re-, and deforestation, and improving the accuracy of carbon accounting. Owing to the 3-dimensional nature of forest structure, remote sensing using airborne LiDAR can be used to perform these measurements of vegetation structure at large scale. Harnessing the full dimensionality of the data, we present deep learning systems predicting wood volume and above ground biomass (AGB) directly from the full LiDAR point cloud and compare results to state-of-the-art approaches operating on basic statistics of the point clouds. For this purpose, we devise different neural network architectures for point cloud regression and evaluate them on remote sensing data of areas for which AGB estimates have been obtained from field measurements in the Danish national forest inventory. Our adaptation of Minkowski convolutional neural networks for regression give the best results. The deep neural networks produce significantly more accurate wood volume, AGB, and carbon stock estimates compared to state-of-the-art approaches. In contrast to other methods, the proposed deep learning approach does not require a digital terrain model and is robust to artifacts along the boundaries of the evaluated areas, which we demonstrate for the case where trees protrude into the area from the outside. We expect this finding to have a strong impact on LiDAR-based analyses of biomass dynamics.

Improving forest above-ground biomass estimation using genetic-based feature selection from Sentinel-1 and Sentinel-2 data (case study of the Noor forest area in Iran)

Biomass holds great importance in the environment, as it not only allows us to measure the carbon stored in forests but also facilitates the assessment of biodiversity and the evaluation of ecological integrity within these crucial ecosystems. In this study, we employed a Genetic Algorithm (GA) to estimate forest Above-Ground Biomass (AGB) by selecting the most applicable features from both Sentinel-2 optical and Sentinel-1 Synthetic Aperture Radar (SAR) images in the Noor forest. The study area was divided into four distinct regions (north, near north, middle, and south), and each region was documented with 100 sample plots through fieldwork to enable comprehensive analysis. In our workflow, Sentinel-2-derived features (i.e., spectral bands, vegetation indices (VIs), soil indices (SIs), and water indices (WIs), along with Sentinel-1 SAR features were initially extracted. Subsequently, GA was employed to select the most optimal features among them within both Random Forest (RF) and Multiple Linear Regression (MLR) models, leading to enhanced accuracy in the forest AGB estimation process. The experimental results demonstrated that the RF model outperformed the MLR model in estimating forest AGB. Furthermore, incorporating GA-based feature selection substantially improved the accuracy of both models, resulting in more dependable AGB estimations. The selected features from the combined Sentinel-1 and Sentinel-2 data also provided the best AGB estimation, surpassing the individual use of each dataset. The selected features from Sentinel-2 particularly played a more substantial role in achieving this overall enhanced performance in AGB estimation. The AGB estimates based on GA-RF were more accurate in all cases, with an average coefficient of determination (R2) of 0.5 and average RMSE of 13.17 Mg ha−1, while the MLR-based estimates were less accurate, with an average R2 value lower than 0.3 and average RMSE higher than 16 Mg ha−1. Furthermore, the GA-RF model selected a wider variety of features including spectral bands, indices, and SAR features compared to GA-MLR, resulting in accurate AGB estimation in the Noor forest.

Forest Aboveground Biomass Estimation in Subtropical Mountain Areas Based on Improved Water Cloud Model and PolSAR Decomposition Using L-Band PolSAR Data

Forest aboveground biomass (AGB) retrieval using synthetic aperture radar (SAR) backscatter has received extensive attention. The water cloud model (WCM), because of its simplicity and physical significance, has been one of the most commonly used models for estimating forest AGB using SAR backscatter. Nevertheless, forest AGB estimation using the WCM is usually based on simplified assumptions and empirical fitting, leading to results that tend to overestimate or underestimate. Moreover, the physical connection between the model and the polarimetric synthetic aperture radar (PolSAR) is not established, which leads to the limitation of the inversion scale. In this paper, based on the fully polarimetric SAR data from the Advanced Land Observing Satellite-2 (ALOS-2) Phased Array-type L-band Synthetic Aperture Radar (PALSAR-2), the relative contributions of the three major scattering mechanisms were first analyzed in a hilly area of southern China. On this basis, the traditional WCM was extended by considering the secondary scattering mechanism. Then, to establish the direct relationship between the vegetation scattering mechanism and forest AGB, a new relationship equation between the PolSAR decomposition model and the improved water cloud model (I-WCM) was constructed without the help of external data. Finally, a nonlinear iterative method was used to estimate the forest AGB. The results show that volume scattering is the dominant mechanism, accounting for more than 60%. Double-bounce scattering accounts for the smallest fraction, but still about 10%, which means that the contribution of the double-bounce scattering component is not negligible in forested areas because of the strong penetration capability of the long-wave SAR. The modified method provides a correlation coefficient R2 of 0.665 and a root mean square error (RMSE) of 21.902, which is an improvement of 36.42% compared to the traditional fitting method. Moreover, it enables the extraction of forest parameters at the pix scale using PolSAR data without the need for low-resolution external data and is thus helpful for high-resolution mapping of forest AGB.

Novel Features of Canopy Height Distribution for Aboveground Biomass Estimation Using Machine Learning: A Case Study in Natural Secondary Forests

Identifying important factors (e.g., features and prediction models) for forest aboveground biomass (AGB) estimation can provide a vital reference for accurate AGB estimation. This study proposed a novel feature of the canopy height distribution (CHD), a function of canopy height, that is useful for describing canopy structure for AGB estimation of natural secondary forests (NSFs) by fitting a bimodal Gaussian function. Three machine learning models (Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (Xgboost)) and three deep learning models (One-dimensional Convolutional Neural Network (1D-CNN4), 1D Visual Geometry Group Network (1D-VGG16), and 1D Residual Network (1D-Resnet34)) were applied. A completely randomized design was utilized to investigate the effects of four feature sets (original CHD features, original LiDAR features, the proposed CHD features fitted by the bimodal Gaussian function, and the LiDAR features selected by the recursive feature elimination algorithm) and models on estimating the AGB of NSFs. Results revealed that the models were the most important factor for AGB estimation, followed by the features. The fitted CHD features significantly outperformed the other three feature sets in most cases. When employing the fitted CHD features, the 1D-Renset34 model demonstrates optimal performance (R2 = 0.80, RMSE = 9.58 Mg/ha, rRMSE = 0.09), surpassing not only other deep learning models (e.g.,1D-VGG16: R2 = 0.65, RMSE = 18.55 Mg/ha, rRMSE = 0.17) but also the best machine learning model (RF: R2 = 0.50, RMSE = 19.42 Mg/ha, rRMSE = 0.16). This study highlights the significant role of the new CHD features fitting a bimodal Gaussian function and the effects between the models and the CHD features, which provide the sound foundations for effective estimation of AGB in NSFs.

Comparing Algorithms for Estimation of Aboveground Biomass in Pinus yunnanensis

Comparing algorithms are crucial for enhancing the accuracy of remote sensing estimations of forest biomass in regions with high heterogeneity. Herein, Sentinel 2A, Sentinel 1A, Landsat 8 OLI, and Digital Elevation Model (DEM) were selected as data sources. A total of 12 algorithms, including 7 types of learners, were utilized for estimating the aboveground biomass (AGB) of Pinus yunnanensis forest. The results showed that: (1) The optimal algorithm (Extreme Gradient Boosting, XGBoost) was selected as the meta-model (referred to as XGBoost-stacking) of the stacking ensemble algorithm, which integrated 11 other algorithms. The R2 value was improved by 0.12 up to 0.61, and RMSE was decreased by 4.53 Mg/ha down to 39.34 Mg/ha compared to the XGBoost. All algorithms consistently showed severe underestimation of AGB in the Pinus yunnanensis forest of Yunnan Province when AGB exceeded 100 Mg/ha. (2) XGBoost-Stacking, XGBoost, BRNN (Bayesian Regularized Neural Network), RF (Random Forest), and QRF (Quantile Random Forest) have good sensitivity to forest AGB. QRNN (Quantile Regression Neural Network), GP (Gaussian Process), and EN (Elastic Network) have more outlier data and their robustness was poor. SVM-RBF (Radial Basis Function Kernel Support Vector Machine), k-NN (K Nearest Neighbors), and SGB (Stochastic Gradient Boosting) algorithms have good robustness, but their sensitivity was poor, and QRF algorithms and BRNN algorithm can estimate low values with higher accuracy. In conclusion, the XGBoost-stacking, XGBoost, and BRNN algorithms have shown promising application prospects in remote sensing estimation of forest biomass. This study could provide a reference for selecting the suitable algorithm for forest AGB estimation.

Improving the Potential of Coniferous Forest Aboveground Biomass Estimation by Integrating C- and L-Band SAR Data with Feature Selection and Non-Parametric Model

Forests play a significant role in terrestrial ecosystems by sequestering carbon, and forest biomass is a crucial indicator of carbon storage potential. However, the single-frequency SAR estimation of forest biomass often leads to saturation issues. This research aims to improve the potential for estimating forest aboveground biomass (AGB) by feature selection based on a scattering mechanism and sensitivity analysis and utilizing a non-parametric model that combines the advantage of dual-frequency SAR data. By employing GF-3 and ALOS-2 data, this study explores the scattering mechanism within a coniferous forest by using results of target decomposition and the pixel statistics method. By selecting an appropriate feature (backscatter coefficients and polarization parameters) and using stepwise regression models and a non-parametric model (the random forest adaptive genetic algorithm (RF-AGA)), the results revealed that the RF-AGA model with feature selection exhibited excellent AGB estimation performance without obvious saturation (RMSE = 10.42 t/ha, R2 = 0.93, leave-one-out cross validation). The σHV, σVH, Pauli three-component decomposition, Yamaguchi three-component decomposition, and VanZyl3 component decomposition of thee C-band and σHV, σVH,σHH, Yamaguchi three-component decomposition, and VanZyl3 component decomposition of the L-band are suited for estimating the AGB of coniferous forests. Volume scattering was the dominant mechanism, followed by surface scattering, while double-bounce scattering had the smallest proportion. This study highlights the potential of investigating scattering mechanisms, sensitivity factors, and parameter selection in the C- and L-band SAR data for improved forest AGB estimation.