Large Forest Areas Research Articles

Propagation Characteristics and Influencing Factors of Meteorological Drought to Soil Drought in the Upper Reaches of the Shiyang River Based on the Copula Function

Drought propagation is a complex process, and understanding the propagation mechanisms of meteorological drought to soil drought is crucial for early warning, disaster prevention, and mitigation. This study focuses on eight tributaries in the upper reaches of the Shiyang River. Based on the Standardized Precipitation Index (SPI) and the Standardized Soil Moisture Index (SSMI), the Drought Propagation Intensity Index (DIP) and Copula function were applied to quantify the intensity and time of drought propagation from meteorological to soil drought and explored the drought propagation patterns at different temporal and spatial scales in these tributaries. Results showed that, in the 0–10 cm soil layer, the propagation intensity of meteorological drought to soil drought was peer-to-peer, with a propagation time of one month. In the middle (10–40 cm) and deep (40–100 cm) soil layers, propagation characteristics differed between the eastern and western tributaries. The western tributaries experienced stronger drought propagation intensity and shorter propagation times (2–4 months), while the eastern tributaries exhibited peer-to-peer propagation intensity with longer times (4–10 months). The large areas of forests and grasslands in the upper reaches of the Shiyang River contributed to strong land–atmosphere interactions, leading to peer-to-peer drought propagation intensity in the 0–10 cm soil layer. The eastern tributaries had extensive cultivated land, where irrigation during meteorological drought enhanced soil moisture, resulting in peer-to-peer propagation intensity in the middle (10–40 cm) and deep (40–100 cm) soil layers. In contrast, the western tributaries, with larger forest areas and widespread permafrost, experienced high water consumption and limited recharge in the 10–40 cm and 40–100 cm soil layers, leading to strong drought propagation.

Growth and globalization of the Central African wildlife economy: Insights from a 23-year study of wild meat markets on Bioko Island, Equatorial Guinea

The commercial trade in wild meat is booming in Central Africa. Addressing this issue is a global priority because the trade poses a major threat to biodiversity and human health. We investigated the impact of socioeconomic factors, public health emergencies, and conservation efforts on the wild meat trade using daily surveys of wild meat markets on Bioko Island, Equatorial Guinea (EG), from 1997 through 2021. Bioko is an ideal location for examining how external factors impact the wild meat market trade. Although small, the island has large areas of intact forest that host populations of commercially valuable wildlife; low-cost protein substitutes are available; and Malabo, the island’s only large metropolitan area and wild meat trading hub, hosts a wealthy class of urbanites. We found significant associations between global market trends and the wild meat trade, especially China’s foreign investment and oil production in the US and EG. Economic crises like EG’s 2009 economic downturn that followed a global crash in oil prices and reduced production, redirected demand towards cheaper mainland wildlife carcasses amid reduced consumer demand. Public health emergencies had the most comprehensive impact on the wild meat trade. The 2014 Ebola outbreak and the COVID-19 pandemic both induced shifts in market demand, and the COVID-19 pandemic disrupted trade routes, affecting both urban and rural markets. Internally, we observed market decentralization over the last decade and changes in wildlife supply chains during public health emergencies. Conservation policies, including anti-poaching measures and educational outreach, temporarily influenced wildlife market trends, sometimes leading to trading surges in endangered primate carcasses. Our study highlights the importance of monitoring global market trends, public health campaigns, and adapting conservation strategies to disrupt wildlife supply chains and curb consumer demand for wild meat.

Forest Fire Severity and Koala Habitat Recovery Assessment Using Pre- and Post-Burn Multitemporal Sentinel-2 Msi Data

Habitat loss due to wildfire is an increasing problem internationally for threatened animal species, particularly tree-dependent and arboreal animals. The koala (Phascolartos cinereus) is endangered in most of its range, and large areas of forest were burnt by widespread wildfires in Australia in 2019/2020, mostly areas dominated by eucalypts, which provide koala habitats. We studied the impact of fire and three subsequent years of recovery on a property in South-East Queensland, Australia. A classified Differenced Normalised Burn Ratio (dNBR) calculated from pre- and post-burn Sentinel-2 scenes encompassing the local study area was used to assess regional impact of fire on koala-habitat forest types. The geometrically structured composite burn index (GeoCBI), a field-based assessment, was used to classify fire severity impact. To detect lower levels of forest recovery, a manual classification of the multitemporal dNBR was used, enabling the direct comparison of images between recovery years. In our regional study area, the most suitable koala habitat occupied only about 2%, and about 10% of that was burnt by wildfire. From the five koala habitat forest types studied, one upland type was burnt more severely and extensively than the others but recovered vigorously after the first year, reaching the same extent of recovery as the other forest types. The two alluvial forest types showed a negligible fire impact, likely due to their sheltered locations. In the second year, all the impacted forest types studied showed further, almost equal, recovery. In the third year of recovery, there was almost no detectable change and therefore no more notable vegetative growth. Our field data revealed that the dNBR can probably only measure the general vegetation present and not tree recovery via epicormic shooting and coppicing. Eucalypt foliage growth is a critical resource for the koala, so field verification seems necessary unless more-accurate remote sensing methods such as hyperspectral imagery can be implemented.

The Change Detection of Mangrove Forests Using Deep Learning with Medium-Resolution Satellite Imagery: A Case Study of Wunbaik Mangrove Forest in Myanmar

This paper presents the development of a U-Net model using four basic optical bands and SRTM data to analyze changes in mangrove forests from 1990 to 2024, with an emphasis on the impact of restoration programs. The model, which employed supervised learning for binary classification by fusing multi-temporal Landsat 8 and Sentinel-2 imagery, achieved a superior accuracy of 99.73% for the 2020 image classification. It was applied to predict the long-term mangrove maps in Wunbaik Mangrove Forest (WMF) and to detect the changes at five-year intervals. The change detection results revealed significant changes in the mangrove forests, with 29.3% deforestation, 5.75% reforestation, and −224.52 ha/yr of annual rate of changes over 34 years. The large areas of mangrove forests have increased since 2010, primarily due to naturally recovered and artificially planted mangroves. Approximately 30% of the increased mangroves from 2015 to 2024 were attributed to mangrove plantations implemented by the government. This study contributes to developing a deep learning model with multi-temporal and multi-source imagery for long-term mangrove monitoring by providing accurate performance and valuable information for effective conservation strategies and restoration programs.

Benchmarking of Individual Tree Segmentation Methods in Mediterranean Forest Based on Point Clouds from Unmanned Aerial Vehicle Imagery and Low-Density Airborne Laser Scanning

Three raster-based (RB) and one point cloud-based (PCB) algorithms were tested to segment individual Aleppo pine trees and extract their tree height (H) and crown diameter (CD) using two types of point clouds generated from two different techniques: (1) Low-Density (≈1.5 points/m2) Airborne Laser Scanning (LD-ALS) and (2) photogrammetry based on high-resolution unmanned aerial vehicle (UAV) images. Through intensive experiments, it was concluded that the tested RB algorithms performed best in the case of UAV point clouds (F1-score > 80.57%, H Pearson’s r > 0.97, and CD Pearson´s r > 0.73), while the PCB algorithm yielded the best results when working with LD-ALS point clouds (F1-score = 89.51%, H Pearson´s r = 0.94, and CD Pearson´s r = 0.57). The best set of algorithm parameters was applied to all plots, i.e., it was not optimized for each plot, in order to develop an automatic pipeline for mapping large areas of Mediterranean forests. In this case, tree detection and height estimation showed good results for both UAV and LD-ALS (F1-score > 85% and >76%, and H Pearson´s r > 0.96 and >0.93, respectively). However, very poor results were found when estimating crown diameter (CD Pearson´s r around 0.20 for both approaches).

Palawan Peacock Pheasant (Polyplectron Napoleonis) Species Distribution Modeling: A Review of the Impact of Typhoon Rai/Odette on the Diversity and Distribution of an Endemic Bird Species

This study quantified the habitat requirements and, consequently, described the remaining suitable habitats through species distribution modeling of Polyplectron napoleonis within Cleopatra’s Needle Forest Reserve and Puerto Princesa Subterranean River National Park after the onslaught of Typhoon Odette in the Palawan region. This was accomplished using MaxEnt software, a statistical machine-learning algorithm that creates niche models with presence-only (PO) data and surrounding environmental variables (Dudik et al., 2007; Merow et al., 2013). Previous studies have identified precipitation, elevation, and land cover as the top environmental variables influencing tandikan habitat suitability, as revealed by their percent contributions. There were earlier claims of the noticeable movement of habitat-suitable areas to the fringes and beyond Cleopatra's Needle Forest Reserve. The migration seems to be going towards highland forests. Two factors could be behind this migration: the tandikan are responding to climate change or avoiding human disturbance. As this species is known to have a high tolerance for temperature change, the latter could be the more plausible factor. For 2022, post-Odette, MaxEnt analysis revealed a shift of percent contributions with elevation and land cover classification outranking aspect and slope. Environmental layers were limited to four, as these were the only currently available data. This shift in percent contributions could be linked to the direct damage to forests brought by the Typhoon in December of 2021. The land cover map generated for this year has shown large areas of forests that were converted into non-forests. Conservation efforts, therefore, for the tandikan, a forest species, should be recalibrated in response to this current development. Further, measures to mitigate the impact of solid typhoons on forests should be reviewed and evaluated.

Economic valuation of carbon sequestration in Quito’s Metropolitan Park using Sentinel-2 and neural networks

This study introduces an innovative method for assessing the economic value of carbon stored by the urban park forest in Quito, Ecuador. The method uses Sentinel-2 remote sensing data and advanced deep learning techniques. A large forest study area was chosen, and detailed field measurements were taken to gather biomass and carbon data. Sentinel-2 satellite images were processed to correct for radiation and atmospheric conditions, and vegetation indices such as NDVI and EVI were calculated. To model forest biomass, a convolutional neural network (CNN) was created and trained using Sentinel-2 spectral bands and vegetation indices. The model was validated with independent field data and demonstrated high accuracy in estimating biomass and carbon, as indicated by evaluation metrics like RMSE and R². The findings include detailed maps showing the spatial distribution of biomass and carbon in the study area, which can be a valuable tool for forest management and the implementation of policies for valuing stored carbon. This approach combines the high resolution of Sentinel-2 data with the predictive power of neural networks, providing a robust and scalable method for estimating carbon across large forest areas. The study's conclusions emphasize the feasibility and accuracy of this approach and its potential for application in various forestry and geographical contexts.

Modelling of atmospheric concentrations of fungal spores: a 2-year simulation over France using CHIMERE

Abstract. Fungal spore organic aerosol emissions have been recognised as a significant source of particulate matter as PM10; however, they are not widely considered in current air quality models. In this work, we have implemented the parameterisation of fungal spore organic aerosol (OA) emissions introduced by Heald and Spracklen (2009) (H&S) and further modified by Hoose et al. (2010) in the CHIMERE regional chemistry-transport model. This simple parameterisation is based on two variables, leaf area index (LAI) and specific humidity. We have validated the geographical and temporal representativeness of this parameterisation on a large scale by using yearly polyol observations and primary biogenic organic aerosol factors from positive matrix factorisation (PMF) analysis at 11 French measurement sites. For a group of sites in northern and eastern France, the seasonal variation of fungal spore emissions, displaying large summer and small winter values, is correctly depicted. However, the H&S parameterisation fails to capture fungal spore concentrations for a smaller group of Mediterranean sites with less data availability in terms of both absolute values and seasonal variability, leading to strong negative biases, especially during the autumn and winter seasons. Two years of CHIMERE simulations with the H&S parameterisation have shown a significant contribution of fungal spore OA to PM10 mass, which is lower than 10 % during winter and reaches up to 20 % during summer in high-emission zones, especially over large forested areas. In terms of contributions to organic matter (OM) concentrations, the simulated fungal spore contribution in autumn is as high as 40 % and reaches at most 30 % of the OM for the other seasons. As a conclusion, the fungal spore OA contribution to the total OM concentrations is shown to be substantial enough to be considered a major PM10 fraction and should then be included in state-of-the-art chemistry-transport models.

Early wildfire detection using different machine learning algorithms

Early detection of wildfires is essential for mitigating their impact on forests and surrounding areas. In this study, we propose a wireless sensor node system that combines multiple low-cost sensors with an artificial intelligence-based detection method for early wildfire detection. The system architecture includes temperature, humidity, and smoke sensors, as well as a wireless communication module. Four machine learning classifiers, including decision trees, random forests, support vector machines, and k-nearest neighbors, were evaluated for their effectiveness in predicting wildfire detection using a dataset collected in a forest area. The results showed that the random forest algorithm with optimum hyperparameters had the highest accuracy in classifying fire and non-fire samples (77.95% correctly classified). The proposed system provides an effective and cost-efficient solution for early wildfire detection in large forest areas.

The Sensory Profile of 5 Types of Sumatran Forest Honey

Sumatra has a very large forest area so it has great potential to become a place for honey bee cultivation. The various honey produced has different characteristics depending on the source of the nectar. Research on sensory testing of Sumatran forest honey appears limited, with studies focusing more broadly on honey quality and properties. It is necessary to collect data on the sensory profile of Sumatran forest honey as a database that will help control the quality and ensure the authenticity of the honey. The purpose of this study is to determine the sensory profile of five types of Sumatran forest honey traded around Lampung Province. The method used a scoring test on color, aroma, taste, and viscosity. 30 trained panelists were used who had been selected and trained before conducting sample assessment. Data processing using ANOVA and further test Duncan Multiple Range Test (DMRT) with SPSS 27.0 software. The results showed that the five types of Sumatran forest honey tested had the same viscosity but had different color, aroma, and taste profiles. These distinctive and unique characteristics can enrich the biodiversity in Indonesia so it needs to be optimized for its benefits and preserved.

Review of forest ecosystem services evaluation studies in East Africa

The East African region hosts diverse forest ecosystems, such as woodlands, highland forests, and coastal mangrove forests. These ecosystems are crucial for biodiversity and support various plant and animal species. They provide essential resources, benefiting livelihoods directly and indirectly. Examining regional and global variations in forest ecosystem valuation, especially regarding livelihood benefits, is crucial for sustainable resource management aligned with forest-based climate solutions. The aim of this review is to assess how regional contextual factors and global trends impact the valuation of ecosystem services (ES) in East Africa, with two main objectives (1) to identify the most evaluated ES in East Africa and (2) to identify the preferred ES valuation methods and approaches applied in East Africa. Data from the Web of Science/Clarivate platform was used in the systematic review process using the Reporting standard for Systematic Evidence Syntheses to retrieve and analyse 222 articles. The ES were categorized using the Millennium Ecosystem Assessment framework and the Common International Classification of Ecosystem Services in order to create a review database. Provisioning services i.e., wood biomass and food production were the most assessed at 55%, followed by 30% regulating services i.e., carbon storage, 8.6% support services i.e., habitat and 6.4% cultural services i.e., ecotourism which reflected communities’ direct reliance on forest resources. The preferred direct ES valuation techniques included market price at 14.9% for assessing provisioning services and travel cost methods at 10.4% for cultural services. Amongst the indirect ES valuation techniques, remote sensing at 14.7% were preferred as they proved efficient for large and remote tropical forest areas. Participatory methods such as interviews at 11.8% were also preferred because they offer holistic perspectives on community priorities. This review provides spatial context on the regional priorities of ES valuation which is vital for safeguarding natural resources for future generations.

Accurate Calculation of Tree Stem Traits in Forests Using Localized Multi-View Registration

Abstract. In recent years, there has been a high demand in forestry and forest research for the accurate measurement of tree traits from point clouds captured by terrestrial laser scanners. However, the reliability of the calculated values is not sufficient due to the difficulty of accurate registration of each tree over a large area of forest. To solve this problem, we introduce localized multi-view registration for correcting the registration matrix of each tree stem. In addition, we discuss methods for registering the whole point clouds of a forest by using the registration matrices locally calculated for tree stems. Especially, we discuss a method to align tree stem points that do not have sufficient overlapping points required in registration. The proposed method was applied to actual forest point clouds and diameter at breast height (DBH) was compared to the manually measured DBH. Experimental results showed that the proposed method was effective in reducing registration errors and in calculating tree stem traits with high accuracy.

Increase the production of giant mud crab (Scylla serata) through the Bieng Samudra Cage in Pauh Tanjung Village River Farmer Group, Langsa City

Potential for the development of the mangrove crab business in the coastal area of the city of Langsa, which has a fairly large mangrove forest area and produces abundant mangrove crab resources. However, some of the results of the study stated that the exploitation and the absence of restrictions on the size of the capture of mangrove crabs resulted in a decrease in the number of catchments by fishermen because the condition of crab stock in nature has decreased. The purpose of dedication is to provide education and training to fishermen about selling mangrove crabs, which is more prioritized than fattening results from direct catches from nature, and to increase the production of mud crabs by utilizing local materials. The next goal is the management of crab capture. Implementation of dedication is carried out through socialization and training for coastal communities and fishermen in Sungai Pauh Tanjung Village, Langsa City. The results of the implementation of community service activities contribute to increasing skills and added value, as well as increasing the production of mangrove crabs through the use of Samudra being cages and the use of local materials as potential feed for fattening mangrove crabs before being sold at the market.

Allometric estimation models for aboveground and belowground biomass of pre-fire and post-fire vegetation in Scots pine forests

Abstract Wildfires have recently destroyed large areas of forest in Central Europe. After a fire, the post-fire vegetation succession rebuilds previously lost biomass and carbon. Nevertheless, ground vegetation and tree regeneration, as well as belowground biomass, are largely neglected in allometric biomass models. Moreover, most models are calibrated for undisturbed forests, which differ from burned forests in terms of site conditions and species composition. We adapted a model using plant cover and shoot length of herb, graminoid and bryophyte species (PhytoCalc), and a single tree model using shoot length and root collar diameter of juvenile trees to estimate aboveground biomass (AGB) of post-fire species and growth groups, and extended them to estimate belowground biomass. We sampled the most dominant species from the herb and moss layer and the tree regeneration of burned and unburned Scots pine (Pinus sylvestris L.) forests in NE Germany. We successfully calibrated post-fire vegetation models and showed that models for undisturbed forests from the literature mostly underestimate post-fire AGB. Using models from the literature for clear-cuts often improved the estimation of post-fire AGB, but still failed to estimate AGB accurately for some species. Inaccurate estimation of post-fire biomass with these other models can be explained by high irradiance and increased nutrient availability on burned sites, which affect tissue and wood density. We showed that own species- and growth group-specific allometric models calibrated to post-fire vegetation are required to correctly estimate the total (above- and belowground) biomass of post-fire vegetation needed to calculate carbon storage.

Analysis of the relationship between L-band SAR backscatter and understory weed density in eucalyptus plantation forests

ABSTRACT This study aims to reveal the relationships between understory coverage (principally, weed growth) beneath the canopies of Sumatran eucalyptus plantations and L-band backscatter data gathered by the PALSAR-2 Synthetic Aperture Radar (SAR) onboard the ALOS-2 satellite. Statistical analysis in conjunction with in situ measurements of forest structural parameters reveals that the SAR polarization ratio is significantly negatively correlated with understory coverage in forests taller than or equal to 10 m or above 2 years of age. Our field investigations confirm that a decrease in canopy coverage takes place some 2 years after transplanting, which in turn permits increased penetration (decreased attenuation) of microwave signals thereby enabling the SAR to detect changes in understory coverage. In addition, both growth and unmanaged remnants of the understory vegetation in older forests reduce evaporation from the ground, which in turn stabilizes soil-moisture levels throughout the year and allows co-polarized backscatter data (which might otherwise be dominated by soil-moisture changes) to contain significant information on the underlying vegetation. No correlation between the understory and SAR backscatter was recorded in younger forests undergoing programs of intensive weed management. This is presumably because strong canopy and trunk backscatter obscured the response from understory vegetation and because artificial changes were induced in vegetation water content as a result of the application of herbicides which in turn reduced the accuracy of some of our field measurements of understory coverage. This research nevertheless demonstrates an important potential application of active satellite microwave remote sensing. We show that satellite-based L-band SAR can be used as a tool to investigate coverage percentages of understory layers. This synoptic technique reduces the need for repeated field surveys across large areas of forest. It can enhance ecosystem assessment and improve understory coverage estimates in sparse forests and in various types of plantations.

OPTIMIZING FOREST AND FORESTRY CONTROL EFFORTS: LEGAL FRAMEWORK AND URGENCY OF REGIONAL REGULATIONS IN CONTROLLING FOREST AND LAND FIRES

Forest and land fires (Karhutla) often occur in Indonesia, triggered by drought due to El Nino-Southern Oscillation (ENSO) or human activity. This research examines the arrangements for controlling forest and land fires in Indonesia and analyzes the basic problems in controlling forest and land fires and explores the urgency of forming related regional regulations. The research method uses a normative juridical approach through statutory and conceptual analysis. The results show basic problems, such as large areas of forest and land, lack of coordination between institutions, unclear management rights, and minimal community participation. The formation of regional regulations is very important to optimize forest and land fires control, because it can adapt strategies to local characteristics and support national policies.

Effects of Illumination Conditions on Individual Tree Height Extraction Using UAV LiDAR: Pilot Study of a Planted Coniferous Stand

Tree height is one of the key dendrometric parameters for indirectly estimating the timber volume or aboveground biomass of a forest. Field measurement is time-consuming and labor-intensive, while unmanned aerial vehicle (UAV)-borne LiDAR is a more efficient tool for acquiring tree heights of large-area forests. Although individual tree heights extracted from point cloud data are of high accuracy, they are still affected by some weather and environment factors. In this study, taking a planted M. glyptostroboides (Metasequoia glyptostroboides Hu & W.C. Cheng) stand as the study object, we preliminarily assessed the effects of various illumination conditions (solar altitude angle and cloud cover) on tree height extraction using UAV LiDAR. The eight point clouds of the target stand were scanned at four time points (sunrise, noon, sunset, and night) in two consecutive days (sunny and overcast), respectively. The point clouds were first classified into ground points and aboveground vegetation points, which accordingly produced digital elevation model (DEM) and digital surface model (DSM). Then, the canopy height model (CHM) was obtained by subtracting DEM from DSM. Subsequently, individual trees were segmented based on the seed points identified by local maxima filtering. Finally, the individual tree heights of sample trees were separately extracted and assessed against the in situ measured values. As results, the R2 and RMSEs of tree heights obtained in the overcast daytime were commonly better than those in the sunny daytime; the R2 and RMSEs at night were superior among all time points, while those at noon were poorest. These indicated that the accuracy of individual tree height extraction had an inverse correlation with the intensity of illumination. To obtain more accurate tree heights for forestry applications, it is best to acquire point cloud data using UAV LiDAR at night, or at least not at noon when the illumination is generally strongest.

Mind the gaps: horizontal canopy structure affects the relationship between taxonomic and spectral diversity

ABSTRACT Spectral diversity (SD) in reflectance can be used to estimate plant taxonomic diversity (TD) according to the Spectral Variation Hypothesis (SVH). However, contrasting relationships between SD and TD have been reported by different studies. Indeed, multiple factors may affect SD, including spatial and spectral scales, vegetation characteristics and the adopted SD computational method. Here, we tested the SVH over 171 plots within a large and heterogeneous forest area in North-Eastern Italy using Sentinel-2 data, aiming at identifying possible factors affecting the strength and direction of SD-TD relationship. SD was determined using ‘biodivMapR’ (BD) and ‘rasterdiv’ (RD) R packages and 38 possible combinations of SD indices, at both α (within a community) and β (among communities) levels, and computational parameters accounting for spatial and spectral scales. Information on vegetation structure was either retrieved from ground-based or LiDAR data. A Random Forest approach was used to disentangle the relationships between SD, TD and vegetation structure, and to identify the best combination of SD computational parameters. At the α-level, we found negative relationship between TD and RD SD indices, which was mainly driven by the presence of gaps within the forest canopy. As regards BD, we found that this algorithm reduced background contribution on SD and was able to differentiate major forest types (broadleaves vs conifers), but derived α-SD indices were marginally correlated with α-TD. At the β-level, we observed a statistically significant positive correlation between BD SD indices and TD (maximum r = 0.24). Finally, we found stronger correlations and R2 when SD indices were calculated using smaller computation windows and over a larger pixels extraction area. Our findings suggest that vegetation cover and structure play a major role, with respect to inter-species spectral differences, in determining α-SD, and that SD might better capture differences in species composition at the landscape-level rather than the richness of individual communities.

Epidemiological and sociodemographic description of snakebite envenoming cases in Paraguay reported between 2015 and 2021

IntroductionSnakebite envenoming (SBE) is a public health problem in Paraguay where the presence of 15 medically important snake species has been reported. Blessed with large forested areas, its economy largely...

Urban Above-Ground Biomass Estimation Using GEDI Laser Data and Optical Remote Sensing Images

Accurate estimating of above-ground biomass (AGB) of vegetation in urbanized areas is essential for urban ecosystem services. NASA’s Global Ecosystem Dynamics Investigation (GEDI) mission can obtain precise terrestrial vegetation structure, which is very useful for AGB estimation in large forested areas. However, the spatial heterogeneity and sparse distribution of vegetation in urban areas lead to great uncertainty in AGB estimation. This study proposes a method for estimating vegetation heights by fusing GEDI laser observations with features extracted from optical images. GEDI is utilized to extract the accurate vegetation canopy height, and the optical images are used to compensate for the spatial incoherence of GEDI. The correlation between the discrete vegetation heights of GEDI observations and image features is constructed using Random Forest (RF) to obtain the vegetation canopy heights in all vegetated areas, thus estimating the AGB. The results in Xuzhou of China using GEDI observations and image features from Sentinel-2 and Landsat-8 satellites indicate that: (1) The method of combining GEDI laser observation data with optical images is effective in estimating AGB, and its estimation accuracy (R2 = 0.58) is higher than that of using only optical images (R2 = 0.45). (2) The total AGB in the shorter vegetation region is higher than the other two in the broadleaf forest and the coniferous forest, but the AGB per unit area is the lowest in the shorter vegetation area at 33.60 Mg/ha, and it is the highest in the coniferous forest at 46.60 Mg/ha. And the highest average AGB occurs in October–December at 59.55 Mg/ha in Xuzhou. (3) The near-infrared band has a greater influence on inverted AGB, followed by textural features. Although more precise information about vegetation should be considered, this paper provides a new method for the AGB estimation and also a way for the evaluation and utilization of urban vegetation space.