Search Results (87)

The background for this study is the limitations of the conventional approach of using deforestation area multiplied by biomass densities or emission factors. We demonstrated how TanDEM-X and GEDI data can be combined to estimate forest Above Ground Biomass (AGB) change at the national scale for Tanzania. The results can be further recalculated to estimate CO₂ emissions and removals from the forest. We used repeated short wavelength, InSAR DEMs from TanDEM-X to derive changes in forest canopy height and combined this with GEDI data to convert such height changes to AGB changes. We estimated AGB change during 2012–2019 to be −2.96 ± 2.44 MT per year. This result cannot be validated, because the true value is unknown. However, we corroborated the results by comparing with other approaches, other datasets, and the results of other studies. In conclusion, TanDEM-X and GEDI can be combined to derive reliable temporal change in AGB at large scales such as a country. An important advantage of the method is that it is not required to have a representative field inventory plot network nor a full coverage DTM. A limitation for applying this method now is the lack of frequent and systematic InSAR elevation data. Full article

Fractional Vegetation Cover (FVC) is an important parameter to reflect vegetation growth and describe plant canopy structure. This study integrates both active and passive remote sensing, capitalizing on the complementary strengths of optical and radar data, and applies various machine learning algorithms to retrieve FVC. The results demonstrate that, for FVC retrieval, the optimal combination of optical remote sensing bands includes B2 (490 nm), B5 (705 nm), B8 (833 nm), B8A (865 nm), and B12 (2190 nm) from Sentinel-2, achieving an Optimal Index Factor (OIF) of 522.50. The LiDAR data of ICESat-2 imagery is more suitable for extracting FVC than that of GEDI imagery, especially at a height of 1.5 m, and the correlation coefficient with the measured FVC is 0.763. The optimal feature variable combinations for FVC retrieval vary among different vegetation types, including synthetic aperture radar, optical remote sensing, and terrain data. Among the three models tested—multiple linear regression, random forest, and support vector machine—the random forest model outperformed the others, with fitting correlation coefficients all exceeding 0.974 and root mean square errors below 0.084. Adding LiDAR data on the basis of optical remote sensing combined with machine learning can effectively improve the accuracy of remote sensing retrieval of vegetation coverage. Full article

National-scale forest inventories such as the Forest Inventory and Analysis (FIA) program in the United States are designed to provide data and estimates that meet target precision at the national and state levels. However, such design-based direct estimates are often not accurate at a smaller geographic scale due to the small sample size. Small area estimation (SAE) techniques provide precise estimates at small domains by borrowing strength from remotely sensed auxiliary information. This study combined the FIA direct estimates with gridded mean canopy heights derived from recently published Global Ecosystem Dynamics Investigation (GEDI) Level 3 data and Landsat data to improve county-level estimates of total and merchantable volume, aboveground biomass, and basal area in the states of Alabama and Mississippi, USA. Compared with the FIA direct estimates, the area-level SAE models reduced root mean square error for all variables of interest. The multi-state SAE models had a mean relative standard error of 0.67. In contrast, single-state models had relative standard errors of 0.54 and 0.59 for Alabama and Mississippi, respectively. Despite GEDI’s limited footprints, this study reveals its potential to reduce direct estimate errors at the sub-state level when combined with Landsat bands through the small area estimation technique. Full article

Accurately estimating the forest canopy height is essential for quantifying forest biomass and carbon storage. Recently, the ICESat-2 and GEDI spaceborne LiDAR missions have significantly advanced global canopy height mapping. However, due to inherent sensor limitations, their footprint-level estimates often show systematic bias. Tall forests tend to be underestimated, while short forests are often overestimated. To address this issue, we used coincident G-LiHT airborne LiDAR measurements to correct footprint-level canopy heights from both ICESat-2 and GEDI, aiming to improve the canopy height retrieval accuracy across Puerto Rico’s tropical forests. The bias-corrected LiDAR dataset was then combined with multi-source predictors derived from Sentinel-1/2 and the 3DEP DEM. Using these inputs, we trained a canopy height inversion model based on the AutoGluon stacking ensemble method. Accuracy assessments show that, compared to models trained on uncorrected single-source LiDAR data, the new model built on the bias-corrected ICESat-2–GEDI fusion outperformed in both overall accuracy and consistency across canopy height gradients. The final model achieved a correlation coefficient (R) of 0.80, with a root mean square error (RMSE) of 3.72 m and a relative RMSE of 0.22. The proposed approach offers a robust and transferable approach for high-resolution canopy structure mapping and provides valuable support for carbon accounting and tropical forest management. Full article

Forest age is a key factor in determining the carbon sequestration capacity and trends of forests. Based on the Google Earth Engine platform and using the topographically complex and climatically diverse Southeastern Tibet as the study area, we propose a new method for forest age estimation that integrates multi-source remote-sensing data with machine learning. The study employs the Continuous Degradation Detection (CODED) algorithm combined with spectral unmixing models and Normalized Difference Fraction Index (NDFI) time series analysis to update forest disturbance information and provide annual forest distribution, mapping young forest distribution. For undisturbed forests, we compared 12 machine-learning models and selected the Random Forest model for age prediction. The input variables include multiscale satellite spectral bands (Sentinel-2 MSI, Landsat series, PROBA-V, MOD09A1), vegetation parameter products (canopy height, productivity), data from the Global Ecosystem Dynamics Investigation (GEDI), multi-band SAR data (C/L), vegetation indices (e.g., NDVI, LAI, FPAR), and environmental factors (climate seasonality, topography). The results indicate that the forests in Southeastern Tibet are predominantly overmature (>120 years), accounting for 87% of the total forest cover, while mature (80–120 years), sub-mature (60–80 years), intermediate-aged (40–60 years), and young forests (< 40 years) represent relatively lower proportions at 9%, 1%, 2%, and 1%, respectively. Forest age exhibits a moderate positive correlation with stem biomass (r = 0.54) and leaf-area index (r = 0.53), but weakly negatively correlated with L-band radar backscatter (HV polarization, r = −0.18). Significant differences in reflectance among different age groups are observed in the 500–1000 nm spectral band, with 100 m resolution PROBA-V data being the most suitable for age prediction. The Random Forest model achieved an overall accuracy of 62% on the independent validation set, with canopy height, L-band radar data, and temperature seasonality being the most important predictors. Compared with 11 other machine-learning models, the Random Forest model demonstrated higher accuracy and stability in estimating forest age under complex terrain and cloudy conditions. This study provides an expandable technical framework for forest age estimation in complex terrain areas, which is of significant scientific and practical value for sustainable forest resource management and global forest resource monitoring. Full article

Traditional remote sensing techniques face notable limitations in accurately estimating forest canopy height. Optical data often suffer from vegetation occlusion, while radar systems, though capable of penetrating foliage, show reduced accuracy in complex terrains. The Global Ecosystem Dynamics Investigation (GEDI), a spaceborne LiDAR mission, offers high-resolution measurements that address these challenges. However, the complexity of waveform processing and the influence of geolocation uncertainty demand rigorous assessment. This study employs GEDI Version 2.0 data, which demonstrates substantial improvement in geolocation accuracy compared to Version 1.0, and integrates airborne laser scanning (ALS) data from the Changbai Mountain forest region to simulate GEDI waveforms. A Monte Carlo-based approach was used to quantify and correct geolocation offsets, resulting in a reduction in the average relative error (defined as the mean of the absolute differences between estimated and reference canopy heights divided by the reference values) in canopy height estimates from 11.92% to 8.55%. Compared to traditional correction strategies, this method demonstrates stronger robustness in heterogeneous forest conditions. The findings emphasize the effectiveness of simulation-based optimization in enhancing the geolocation accuracy and canopy height retrieval reliability of GEDI data, especially in complex terrain environments. This contributes to more precise global forest structure assessments and provides a methodological foundation for future improvements in spaceborne LiDAR applications. Full article

Regular measurement of carbon stock in the world’s forests is critical for carbon accounting and reporting under national and international climate initiatives and for scientific research but has been largely limited in scalability and temporal resolution due to a lack of ground-based assessments. Increasing efforts have been made to address these challenges by incorporating remotely sensed data. We present a new methodology that uses multi-sensor, multispectral imagery at a resolution of 10 m and a deep learning-based model that unifies the prediction of aboveground biomass density (AGBD), canopy height (CH), and canopy cover (CC), as well as uncertainty estimations for all three quantities. The model architecture is a custom Feature Pyramid Network consisting of an encoder, decoder, and multiple prediction heads, all based on convolutional neural networks. It is trained on millions of globally sampled GEDI-L2/L4 measurements. We validate the capability of the model by deploying it over the entire globe for the year 2023 as well as annually from 2016 to 2023 over selected areas. The model achieves a mean absolute error for AGBD (CH, CC) of 26.1 Mg/ha (3.7 m, 9.9%) and a root mean squared error of 50.6 Mg/ha (5.4 m, 15.8%) on a globally sampled test dataset, demonstrating a significant improvement over previously published results. We also report the model performance against independently collected ground measurements published in the literature, which show a high degree of correlation across varying conditions. We further show that our pre-trained model facilitates seamless transferability to other GEDI variables due to its multi-head architecture. Full article

Accurately monitoring forest canopy height is crucial for sustainable forest management, particularly in southeastern North Carolina, USA, where dense forests and limited accessibility pose substantial challenges. This study presents an explainable machine learning framework that integrates sparse GEDI LiDAR samples with multi-sensor remote sensing data to improve both the accuracy and interpretability of forest canopy height estimation. This framework incorporates multitemporal optical observations from Sentinel-2; C-band backscatter and InSAR coherence from Sentinel-1; quad-polarization L-Band backscatter and polarimetric decompositions from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR); texture features from the National Agriculture Imagery Program (NAIP) aerial photography; and topographic data derived from an airborne LiDAR-based digital elevation model. We evaluated four machine learning algorithms, K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and eXtreme gradient boosting (XGB), and found consistent accuracy across all models. Our evaluation highlights our method’s robustness, evidenced by closely matched R² and RMSE values across models: KNN (R² of 0.496, RMSE of 5.13 m), RF (R² of 0.510, RMSE of 5.06 m), SVM (R² of 0.544, RMSE of 4.88 m), and XGB (R² of 0.548, RMSE of 4.85 m). The integration of comprehensive feature sets, as opposed to subsets, yielded better results, underscoring the value of using multisource remotely sensed data. Crucially, SHapley Additive exPlanations (SHAP) revealed the multi-seasonal red-edge spectral bands of Sentinel-2 as dominant predictors across models, while volume scattering from UAVSAR emerged as a key driver in tree-based algorithms. This study underscores the complementary nature of multi-sensor data and highlights the interpretability of our models. By offering spatially continuous, high-quality canopy height estimates, this cost-effective, data-driven approach advances large-scale forest management and environmental monitoring, paving the way for improved decision-making and conservation strategies. Full article

Estimates of tree species diversity via traditional optical remote sensing are based only on the spectral variation hypothesis (SVH); however, this approach does not account for the vertical structure of a forest. The relative height (RH) indices derived from GEDI spaceborne LiDAR provide vertical vegetation structure information through waveform decomposition. Although RH indices have been widely studied, the optimal RH index for tree species diversity estimation remains unclear. This study integrated GF-1 optical imagery and GEDI LiDAR data to estimate tree species diversity in a warm temperate forest. First, random forest plus residual kriging (RFRK) was employed to achieve wall-to-wall mapping of the GEDI-derived indices. Second, recursive feature elimination (RFE) was applied to select relevant spectral and LiDAR features. The random forest (RF), support vector machine (SVM), and k-nearest neighbor (kNN) methods were subsequently applied to estimate tree species diversity through remote sensing data. The results indicated that multisource data achieved greater accuracy in tree species diversity estimation (average R² = 0.675, average RMSE = 0.750) than single-source data (average R² = 0.636, average RMSE = 0.754). Among the three machine learning methods, the RF model (R² = 0.760, RMSE = 2.090, MAE = 1.624) was significantly more accurate than the SVM (R² = 0.571, RMSE = 2.556, MAE = 1.995) and kNN (R² = 0.715, RMSE = 2.084, MAE = 1.555) models. Moreover, mean_mNDVI, mean_RDVI, and mean_Blue were identified as the most important spectral features, whereas RH30 and RH98 were crucial features derived from LiDAR for establishing models of tree species diversity. Spatially, tree species diversity was high in the west and low in the east in the study area. This study highlights the potential of integrating optical imagery and spaceborne LiDAR for tree species diversity modeling and emphasizes that low RH indices are most indicative of middle- to lower-canopy tree species diversity. Full article

Biomass carbon sequestration and sink capacities of tropical rainforests are vital for addressing climate change. However, canopy height must be accurately estimated to determine carbon sink potential and implement effective forest management. Four advanced machine-learning algorithms—random forest (RF), gradient boosting decision tree, convolutional neural network, and backpropagation neural network—were compared in terms of forest canopy height in the Hainan Tropical Rainforest National Park. A total of 140 field survey plots and 315 unmanned aerial vehicle photogrammetry plots, along with multi-modal remote sensing datasets (including GEDI and ICESat-2 satellite-carried LiDAR data, Landsat images, and environmental information) were used to validate forest canopy height from 2003 to 2023. The results showed that RH80 was the optimal choice for the prediction model regarding percentile selection, and the RF algorithm exhibited the optimal performance in terms of accuracy and stability, with R² values of 0.71 and 0.60 for the training and testing sets, respectively, and a relative root mean square error of 21.36%. The RH80 percentile model using the RF algorithm was employed to estimate the forest canopy height distribution in the Hainan Tropical Rainforest National Park from 2003 to 2023, and the canopy heights of five forest types (tropical lowland rainforests, tropical montane cloud forests, tropical seasonal rainforests, tropical montane rainforests, and tropical coniferous forests) were calculated. The study found that from 2003 to 2023, the canopy height in the Hainan Tropical Rainforest National Park showed an overall increasing trend, ranging from 2.95 to 22.02 m. The tropical montane cloud forest had the highest average canopy height, while the tropical seasonal forest exhibited the fastest growth. The findings provide valuable insights for a deeper understanding of the growth dynamics of tropical rainforests. Full article

Changes in carbon stock are a key indicator for assessing the carbon-pool function and the impact of regional carbon cycling on climate. Mangroves, as an essential component of coastal ecosystems, play a critical role in carbon sequestration. However, traditional carbon-sink assessments often overlook biophysical differences between mangrove species and depend on field measurements, which are constrained by the challenging geographical conditions of the intertidal zone. This leads to biases and operational difficulties in estimating carbon stock. To address these challenges, this study proposes a fine-scale method for inter-species carbon-stock assessment, integrating mangrove three-dimensional structural information and spectral characteristics through Google Earth Engine (GEE). By combining GEDI data and Sentinel-2 imagery, this approach incorporates both vertical structure and spectral characteristics, overcoming the limitations of traditional models that neglect inter-species differences and vertical structural information. As a result, the accuracy of carbon-stock estimation is significantly improved. Unlike previous studies, this paper achieves a fully remote sensing-based partial carbon-stock assessment for mangrove species and quantifies carbon stock using the InVEST model, addressing the limitations of previous carbon-sink models. Specifically, on the GEE platform, Sentinel-2 imagery is used for inter-species classification through a random forest (RF) model, while a relationship model between canopy height and biomass is established using GEDI data to estimate biomass. To optimize feature selection, this study introduces a forward feature selection (FFS) approach, which incrementally selects the most predictive features, enhancing the stability and accuracy of the model. By combining biomass and classification results, a remote sensing-based carbon-sink assessment for mangroves is achieved. The study quantifies and visualizes the carbon stock of different mangrove species in Dongzhaigang, revealing that the region’s annual carbon stock totals 302,558.77 t. This validates the superiority and accuracy of the proposed method. Full article

Estimating aboveground biomass (AGB) is vital for sustainable forest management and helps to understand the contributions of forests to carbon storage and emission goals. In this study, the effectiveness of plot-level AGB estimation using height and crown diameter derived from UAV-LiDAR, calibration of GEDI-L4A AGB and GEDI-L2A rh98 heights, and spectral variables derived from UAV-multispectral and RGB data were assessed. These calibrated AGB and height values and UAV-derived spectral variables were used to fit AGB estimations using a random forest (RF) regression model in Fuling District, China. Using Pearson correlation analysis, we identified 10 of the most important predictor variables in the AGB prediction model, including calibrated GEDI AGB and height, Visible Atmospherically Resistant Index green (VARIg), Red Blue Ratio Index (RBRI), Difference Vegetation Index (DVI), canopy cover (CC), Atmospherically Resistant Vegetation Index (ARVI), Red-Edge Normalized Difference Vegetation Index (NDVIre), Color Index of Vegetation (CIVI), elevation, and slope. The results showed that, in general, the second model based on calibrated AGB and height, Sentinel-2 indices, slope and elevation, and spectral variables from UAV-multispectral and RGB datasets with evaluation metric (for training: R² = 0.941 Mg/ha, RMSE = 13.514 Mg/ha, MAE = 8.136 Mg/ha) performed better than the first model with AGB prediction. The result was between 23.45 Mg/ha and 301.81 Mg/ha, and the standard error was between 0.14 Mg/ha and 10.18 Mg/ha. This hybrid approach significantly improves AGB prediction accuracy and addresses uncertainties in AGB prediction modeling. The findings provide a robust framework for enhancing forest carbon stock assessment and contribute to global-scale AGB monitoring, advancing methodologies for sustainable forest management and ecological research. Full article

Forest canopy height (FCH) is a vital indicator for assessing forest health and ecosystem service capacity. Over the past two decades, full-waveform (FW) LiDAR has been widely employed for estimating forest biophysical variables due to its high precision in measuring vertical forest structures. However, the impact of terrain undulations on forest parameter estimation remains challenging. To address this issue, this study proposes a bisection approximation decomposition (BAD) method for processing GEDI L1B data and FCH estimation. The BAD method analyzes the energy composition of simplified echo signals and determines the fitting parameters by integrating overall signal energy, the differences in unresolved signals, and the similarity of inter-forest signal characteristics. FCH is subsequently estimated based on waveform peak positions. By dynamically adjusting segmentation points and Gaussian fitting parameters, the BAD method achieved precise separation of mixed canopy and ground signals, substantially enhancing the physical realism and applicability of decomposition results. The effectiveness and robustness of the BAD method for FCH estimation were evaluated using 2049 footprints across varying slope conditions in the Harvard Forest region of Petersham, Massachusetts. The results demonstrated that digital terrain models (DTMs) extracted using the GEDI data and the BAD method exhibited high consistency with the DTMs derived using airborne laser scanning (ALS) data (coefficient of determination R² > 0.99). Compared with traditional Gaussian decomposition (GD), wavelet decomposition (WD), and deconvolution decomposition (DD) methods, the BAD method showed significant advantages in FCH estimation, achieved the smallest relative root mean square error (rRMSE) of 17.19% and greatest mean estimation accuracy of 84.57%, and reduced the rRMSE by 10.74%, 21.49%, and 28.93% compared to GD, WD, and DD methods, respectively. Moreover, the BAD method exhibited a significantly stronger correlation with ALS-derived canopy height mode data than the relative height metrics from GEDI L2A products (r = 0.84, p < 0.01). The robustness and adaptability of the BAD method to complex terrain conditions provide great potential for forest parameters using GEDI data. Full article

Developing the capacity to monitor species diversity worldwide is of great importance in halting biodiversity loss. To this end, remote sensing plays a unique role. In this study, we evaluate the potential of Global Ecosystem Dynamics Investigation (GEDI) data, combined with conventional satellite optical imagery and climate reanalysis data, to predict in situ alpha diversity (Species richness, Simpson index, and Shannon index) among tree species. Data from Sentinel-2 optical imagery, ERA-5 climate data, SRTM-DEM imagery, and simulated GEDI data were selected for the characterization of diversity in four study areas. The integration of ancillary data can improve biodiversity metrics predictions. Random Forest (RF) regression models were suitable for estimating tree species diversity indices from remote sensing variables. From these models, we generated diversity index maps for the entire Cerrado using all GEDI data available in orbit. For all models, the structural metric Foliage Height Diversity (FHD) was selected; the Renormalized Difference Vegetation Index (RDVI) was also selected in all species diversity models. For the Shannon model, two GEDI variables were selected. Overall, the models indicated performances for species diversity ranging from (R² = 0.24 to 0.56). In terms of RMSE%, the Shannon model had the lowest value among the diversity indices (31.98%). Our results suggested that the developed models are valuable tools for assessing species diversity in tropical savanna ecosystems, although each model can be chosen based on the objectives of a given study, the target amount of performance/error, and the availability of data. Full article

Quantifying forest carbon storage to better manage climate change and its effects requires accurate estimation of forest structural parameters such as canopy height. Variables from remote sensing data and machine learning models are tools that are being increasingly used for this purpose. This study modeled the canopy height of forest–savanna mosaics in the Sudano–Guinean zone of Togo. Relative heights were extracted from GEDI and ICESat-2 products, which were combined with optical, radar, and topographic variables for canopy height modeling. We tested four methods: Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN). The RF algorithm obtained the best predictions using 98% relative height (RH98). The best-performing result was obtained from variables extracted from GEDI data (r = 0.84; RMSE = 4.15 m; MAE = 2.36 m) and compared to ICESat-2 (r = 0.65; RMSE = 5.10 m; MAE = 3.80 m). Models that were developed during this study can be applied over large areas in forest–savanna mosaics, enhancing forest dynamics monitoring in line with REDD+ objectives. This study provides valuable insights for future spaceborne LiDAR and other remote sensing data applications in similar complex ecosystems and offers local decision-makers a robust tool for forest management. Full article