Forest Resources Research Articles

Development of an Algorithm for Assessing the Scope of Large Forest Fire Using VIIRS-Based Data and Machine Learning

Forest fires pose a multifaceted threat, encompassing human lives and property loss, forest resource destruction, and toxic gas release. This crucial disaster’s global occurrence and impact have risen in recent years, primarily driven by climate change. Hence, the scope and frequency of forest fires must be collected to establish disaster prevention policies and conduct relevant research projects. However, some countries do not share details, including the location of forest fires, which can make research problematic when it is necessary to know the exact location or shape of a forest fire. This non-disclosure warrants remote surveys of forest fire sites using satellites, which sidestep national information disclosure policies. Meanwhile, original data from satellites have a great advantage in terms of data acquisition in that they are independent of national information disclosure policies, making them the most effective method that can be used for environmental monitoring and disaster monitoring. The Visible Infrared Imaging Radiometer Suite (VIIRS) aboard the Suomi National Polar-Orbiting Partnership (NPP) satellite has worldwide coverage at a daily temporal resolution and spatial resolution of 375 m. It is widely used for detecting hotspots worldwide, enabling the recognition of forest fires and affected areas. However, information collection on affected regions and durations based on raw data necessitates identifying and filtering hotspots caused by industrial activities. Therefore, this study used VIIRS hotspot data collected over long periods and the Spatio-Temporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN) algorithm to develop ST-MASK, which masks said hotspots. By targeting the concentrated and fixed nature of these hotspots, ST-MASK is developed and used to distinguish forest fires from other hotspots, even in mountainous areas, and through an outlier detection algorithm, it generates identified forest fire areas, which will ultimately allow for the creation of a global forest fire watch system.

Prioritization of Forest Resources for Sustainable Management of Iyiocha Stream Forest Reserve, Delta State, Nigeria

Prioritization of Forest Resources for Sustainable Management of Iyiocha Stream Forest Reserve, Delta State, Nigeria

State and ameliorative properties of old original oak stands

The ameliorative properties of forest stands are essential for developing effective measures for environmental protection and sustainable use of forest resources. The purpose of the study was to assess the current condition and performance of erosion control properties of old oak stands of natural origin. The method of assessing the condition of old oak plantations using an integral indicator that takes into account biometric, ameliorative and health characteristics of stands, as well as agrochemical indicators of the soil has been tested. Field work was carried out on four experimental plots, where 794 age-old trees were enumerated. Comprehensive studies included determination of biometric indicators, analysis of root systems, detection of the content of available forms of nitrogen, mobile phosphorus, mobile potassium in soil. Soil hardness was measured with a durometer and soil water permeability using steel cylinders. High values of integral indicators were obtained in the experimental areas, which range from 11.9 to 19.7%. They guarantee the effective performance of erosion control properties by native old-growth forests. It has been researched that the proposed integral indicator of forest stand condition not only allows for assessing their current state but also demonstrates the effective control of erosion and ecological functions of the stand. It was established that essential requirement is to convert the absolute values of various indicators into relative values, with mandatory consideration of their positive or negative impacts on the forest stands themselves. It was found that an integral condition indicator can be used for erosion control plantations of any age range. The results can be used to develop biodiversity conservation programs and establish effective strategies for managing forest resources

An Insight of Village Community Banks as the Tool of Forest Resource Conservation: A Case of Selected Villages Adjacent Pugu and Kazimzumbwi Forest Reserve.

An Insight of Village Community Banks as the Tool of Forest Resource Conservation: A Case of Selected Villages Adjacent Pugu and Kazimzumbwi Forest Reserve.

A systematic analysis of European markers of balanced environmental management under the conditions of economic circularity

The main task of the article is to research the role of balanced environmental management in the construction of a circular model of the European countries’ economy by using environmental and economic markers. It determines the level of environmental pollution and other environmental problems, including those caused by resource waste. It proposes a technological method of wastewater treatment from estrogen, microplastic particles and oil by using iron oxide. The rate of population for which secondary wastewater treatment is available and its importance for water efficiency under the conditions of significant water crisis in Europe was determined. The paper identifies the main indicators of economic losses of European countries that depend on climate change, because the weather anomalies have a significant impact on economic processes. It studies the dynamics of changes in the area of forested land according to FAO of the European G7 members, the current potential of forest resources of Ukraine and identifies the necessity of systematic electronic wood accounting. It is established that in the EU countries the practice of returning many types of raw materials to production after waste processing has long been accepted, and the need for the fastest possible introduction of innovative processing technologies is identified. Mathematical formulas for calculating the coefficient of cyclicality, circular use of materials and establishes the level of using cyclical materials by European manufacturers are derived. It is established that to identify the efficiency and dynamism of waste transformation, it is appropriate to use an indicator that measures the fraction of recycled household waste in the total volume of its generation. The article establishes the share of fossil fuels in the total available energy of European countries and analyses the dynamics of primary energy consumption based on the example of the Scandinavian countries. It identifies the level of revenues from environmental taxes in most European countries and their importance for the circular economy. It is recommended for Ukraine to study and use the experience of the European Union countries for construction its own model of circular economy based on the principles of balanced nature management and sustainable development.

Floristic Diversity of Natural Forest Patches Across Agroclimatic Zones in Northwestern Ethiopian

Background Natural forest resources in northwestern Ethiopia are currently under threat, requiring immediate conservation measures and a management strategy. Thus, an understanding of the present floristic diversity status is required. There is lack of such type of studies specific to fragmented forest patches and across environmental factors. Consequently, this study aimed to examine the existing state of these resources to apply sustainable forest management practices. Methods To achieve this, transects with 200 square plots measuring 400 m2 were set up at nine forest patches with 200m spacing between plots and transects. Vegetation and environmental data were collected and analyzed using R version 4.1. Results Significant variations (p 0.008) were found in vegetation features along the slope, forest patches, and agroclimatic zone. When compared to other forest patches, highland, and mid-altitude forest patches had the highest species diversity (2.48) and stocking (2578 trees/ha). The gentle slope has the most species diversity (2.83). The species similarity between highland and mid-altitude forest habitats was found significant (69%). The vegetation cover in the mid-altitude forest patches was also high (abundance: 5-12%). In all the forest patches examined, tree life forms exceeded shrubs, climbers, and herbs. Conclusions According to the study’s findings, the state of forest resources varies considerably across different environmental variations. Despite the impression of entire forest patches from the outside, the interiors are open, with only huge and mature trees covering the canopy. This state has been triggered by deforestation, degradation, and inappropriate human and grazing operations.

Unique Plant Resources and Distribution Patterns in the Valley Forest of the Irtysh River Basin.

The river valley forests of the Irtysh River Basin are a germplasm bank of Salicaceae species and rare plant resources in China, and the distribution varies with the river and is highly distinctive. However, there is a dearth of systematic research on the characteristics of plant resources. In this study, a comprehensive investigation was conducted in the trunk stream and six tributaries with valley forest distribution in the Irtysh River Basin, and 244 quadrats were set up. The analysis focused on the composition of the flora and resource characteristics. The results reveal the following: (1) The valley forests of the Irtysh River Basin contain 256 species of plants belonging to 57 families and 178 genera, among which 19 species of trees, 23 species of shrubs, and 214 species of herbs were investigated. (2) Among the identified species, 226 (88.67%) were recognized as resource plants, with medicinal plants being the most abundant (176 species, 68.75% of the total). (3) The distribution patterns of trees, shrubs, and herbs of each resource type vary across rivers. Elevation drop, river length, and river distance all significantly affect the number of specie. This study elucidated the current status and distributional characteristics of plant resources in the valley forests of the Irtysh River Basin, which is essential for both biodiversity conservation and sustainable resource utilization.

China's future forest carbon sequestration potential under different management scenarios

Enhancing forest carbon storage and carbon sequestration capacity is crucial for achieving carbon neutrality. Scientific forest management can maintain a high level of carbon sequestration capacity in forests, and considering the carbon pool of wood products can extend the time of carbon fixation. However, current predictions of large-scale forest carbon storage and carbon sequestration capacity have overlooked changes in forest carbon absorption with forest age and the buffering effect of wood product carbon pools in the carbon release process. In this paper, we used the Forest Simulation and Optimization System model (FSOS) to analyze the wood supply and carbon sequestration capacities of different management scenarios based on data from the Forest Resources Inventory (2014–2018). The results showed that China's forests could export significant amounts of timber in the future; According to the 9th forest survey report, China's forests produce only 88 million m3 yr-1. Among them, the harvested objects were mainly planted forests, and if all forests (planted forests and natural forests) are involved in forest management planning, the maximum sustainable annual wood supply will reach 286 million m3 yr-1. Moreover, due to the current large proportion of younger forests in China, 358 million m3 of annual wood supply will be achievable in the future (as of the year 2039). Forest management can increase the carbon sequestration capacities in forest ecosystems as well as the wood supply compared to the no management options. In summary, the carbon sequestration potential of unmanaged forests is limited. Appropriate forest management can increase the carbon sequestration potential of forests. The substitution of carbon emission reduction of wood products and bioenergy can also greatly reduce the pressure to achieve carbon neutral strategies.

Spatial Distribution Patterns and Influencing Factors of Dominant Species in Plain Valley Forests of the Irtysh River Basin

The Irtysh River, which stretches for 633 km, is the second longest river in Xinjiang. The valley forests within its basin are unique forest resources that exhibit crucial ecological functions and form an integral part of China’s “Three North” Shelterbelt Forest Project. However, previous studies mainly focused on individual tributaries or main streams, lacking comprehensive research on the overall river and valley forest resources and their ecological functions. To address this research gap based on comprehensive investigations, this study analyzed the dominant species composition, spatial distribution patterns, and influencing factors of valley forests across various branches of the Irtysh River basin plain. The results revealed the presence of 10 local tree species in the area, with Populus laurifolia, Populus alba, Salix alba, and Betula pendula as the dominant species. However, seedling regeneration was relatively weak. P. laurifolia, P. alba, and S. alba were widely distributed across tributaries and main streams, whereas B. pendula was primarily found in the tributaries. The four dominant species exhibited distinct clustering patterns. The concentration intensity of these dominant species in the main stream of the Irtysh River basin was significantly higher than those in other tributaries, with P. laurifolia showing a lower concentration intensity across the entire basin than the other dominant species. Negative density dependence was the primary biological factor influencing species aggregation intensity, with significant positive effects on P. alba and S. alba and significant negative effects on B. pendula. Among the abiotic factors, elevation had a significant positive effect on the aggregation intensities of P. alba, S. alba, and B. pendula, indicating that these species tend to aggregate more densely at higher elevations. Conversely, slope had a significant negative impact on the aggregation intensities of P. laurifolia, P. alba, and S. alba, suggesting that increasing slope steepness leads to a decrease in the clustering of these species. Similarly, the distance from the river channel had a significant negative effect on the aggregation intensities of S. alba and B. pendula, implying that as the distance from the river increases, the clustering patterns of these species become less pronounced. This study aimed to detail the current state of valley forest resources and their ecological functions, thereby laying a foundation for their effective protection.

Do government resource management policies influence green productivity? New perspectives from fintech and digital resource policy in China

Achieving sustainable development necessitates the exploration of innovative approaches towards low-carbon development and efficient resource management. By adopting the low-carbon city pilot project as a policy shock of Government Resource Management Policies (GRMP), we aim to scrutinize the nuanced impacts of GRMP on green productivity (GTFP). Using the difference-in-difference (DID) approach and panel data from 280 cities in China. Our findings reveal a significant relationship between GRMP and GTFP. In the immediate short-term, GRMP exhibits a negative effect on GTFP growth, followed by a long-term positive promoting effect. A detailed temporal analysis uncovers an “inverted N″ time-period effect of GRMP on GTFP growth. Further exploration into the mechanisms driving this influence reveals three key aspects: the reduction of natural resources consumption and the promotion of low-carbon production (LCP), low-carbon transportation (LCT), and low-carbon industries (LCI). While the regulated effect of financial technology resources on the relationship between GRMP and GTFP is positive but statistically insignificant, the regulated effect of digital resource policy emerges as positive and significant. Additionally, the regulated effect of mineral and forest resource coverage rate is positive but not statistically significant in the context of the influence of GRMP on GTFP. This comprehensive analysis contributes to our understanding of the dynamic interplay between policy interventions, resource management, and sustainable development in the Chinese urban landscape.

Assessment of Community Participation in Forest Conservation in Ondo State, Nigeria

This study examines community participation in forest conservation in Ondo State, Nigeria, exploring the socio-economic dynamics and the effectiveness of decentralized forest management. Amidst escalating environmental degradation and forest depletion, this research highlights the critical role local communities’ play in the stewardship of forest reserves. Data were collected through surveys, interviews, and field observations involving 200 households across multiple communities adjacent to forest reserves. The findings reveal a strong community willingness to engage in forest conservation, with a substantial proportion of respondents prepared to accept financial incentives to aid in conservation efforts. The study also uncovers a significant correlation between socioeconomic factors—such as income levels, educational attainment, and proximity to forests—and the willingness to participate in conservation initiatives. Despite the readiness to support forest preservation, the research identifies a glaring lack of awareness and involvement in existing forest conservation programs. It is recommended that enhanced community education on the benefits of forest conservation, the introduction of more robust economic incentives, increased community involvement in conservation decision-making, and the strengthening of legal frameworks to protect forest resources. These steps are essential for sustainable forest management and biodiversity conservation in the area, which could serve as a model for similar regions globally.

Carbon storage-driven multi-objective spatial planning: simulation and practice at the management unit level in Northeast China

In recent years, global attention to forest ecological environment, carbon, wood yield, and biodiversity has been increasing, which requires forest managers to make reasonable forest planning in time and space to meet the needs of multi-objectives and multi-resources. In this study, the resources of business units in Northeast China were analyzed, and the FPS-ATLAS model was established. A multi-objective decision supporting spatial forest planning scheme for 16629.53 ha of forest in Jingouling forest farm of Wangqing Forestry Bureau in Jilin Province was proposed. In this paper, the volume growth model of six forest types was established, and the carbon storage model was introduced to show the total carbon, biomass carbon, dissolved organic carbon, and total soil carbon of the ecosystem. The dynamic change in carbon during the whole planning period has achieved good results. After 20 time periods, the total soil carbon increased to 7,627,208 Mg (+6.63%), the total ecosystem carbon increased to 14,889,876 Mg (+27.51%), the biomass carbon increased to 5,362,779 Mg (+59.70%), and the dissolved organic carbon increased to 9,531,906 Mg (+14.59%). The purpose of this article is to achieve dynamic management of forest resources, meet multiple constraint settings, achieve multiple management objectives, harvest wood products, and ensure the ecological and social functions of forests so that forests ultimately achieve the ideal state of sustainability.

Study on the influence of landscape pattern on the spread of pine wilt disease from a multi-scale perspective

Since the introduction of pine wilt disease (PWD) into Chongqing, China, it has been continuously spreading, posing a significant threat to the local forest ecosystem dominated by pine forests. Utilizing data spanning the last two decades on the PWD epidemic subcompartment and host coniferous forest in Chongqing, this study employs a geographic detector model to scrutinize the impact of forest landscape patterns on PWD dissemination at the county, township, and 1 km grid scales. The findings reveal three distinct stages of the PWD epidemic in Chongqing from 2001 to 2020: diffusion, stabilization, and outbreak. The western and central regions of Chongqing experienced severe impacts, while the southern part exhibited relatively milder effects. Across the three spatial scales, various landscape pattern indices exhibit robust and consistent impacts on PWD occurrence. Notably, patch area emerges as the most influential factor, with an explanatory power reaching 0.228. Additionally, landscape shape index, number of patches, patch density, river and road exert substantial influence on PWD incidence. Conversely, the impact of edge density, landscape dominance, landscape separation, and landscape fragmentation on PWD occurrence is comparatively weak. Moreover, the interaction of different landscape pattern factors nonlinearly enhances the explanatory power of PWD occurrence. Among these interactions, the synergy between patch area and landscape dominance proves to have the highest explanatory power for the spatial differentiation of PWD at 0.718. This study explores the relationship between the invasion and spread of PWD and landscape patterns, offering useful insights for the prevention and early warning of PWD. Additionally, this research provides valuable reference points for promoting the healthy and sustainable development of forest resources in China.

Forest Fire Prediction Based on Time Series Networks and Remote Sensing Images

Protecting forest resources and preventing forest fires are vital for social development and public well-being. However, current research studies on forest fire warning systems often focus on extensive geographic areas like states, counties, and provinces. This approach lacks the precision and detail needed for predicting fires in smaller regions. To address this gap, we propose a Transformer-based time series forecasting model aimed at improving the accuracy of forest fire predictions in smaller areas. Our study focuses on Quanzhou County, Guilin City, Guangxi Province, China. We utilized time series data from 2021 to 2022, along with remote sensing images and ArcGIS technology, to identify various factors influencing forest fires in this region. We established a time series dataset containing twelve influencing factors, each labeled with forest fire occurrences. By integrating these data with the Transformer model, we generated forest fire danger level prediction maps for Quanzhou County. Our model’s performance is compared with other deep learning methods using metrics such as RMSE, and the results reveal that the proposed Transformer model achieves higher accuracy (ACC = 0.903, MAPE = 0.259, MAE = 0.053, RMSE = 0.389). This study demonstrates that the Transformer model effectively takes advantage of spatial background information and the periodicity of forest fire factors, significantly enhancing predictive accuracy.

Extraction of Arbors from Terrestrial Laser Scanning Data Based on Trunk Axis Fitting

Accurate arbor extraction is an important element of forest surveys. However, the presence of shrubs can interfere with the extraction of arbors. Addressing the issues of low accuracy and weak generalizability in existing Terrestrial Laser Scanning (TLS) arbor point clouds extraction methods, this study proposes a trunk axis fitting (TAF) method for arbor extraction. After separating the point cloud data by upper and lower, slicing, clustering, fitting circles, obtaining the main central axis, filtering by distance, etc. The canopy point clouds are merged with the extracted trunk point clouds to precisely separate arbors and shrubs. The advantage of the TAF method proposed in this study is that it is not affected by point cloud density or the degree of trunk curvature. This study focuses on a natural forest plot in Shangri-La City, Yunnan Province, and a plantation plot in Kunming City, using manually extracted data from a standardized dataset of samples to test the accuracy of the TAF method and validate the feasibility of the proposed method. The results showed that the TAF method proposed in this study has high extraction accuracy. It can effectively avoid the problem of trunk point cloud loss caused by tree growth curvature. The experimental accuracy for both plots reached over 99%. This study can provide certain technical support for arbor parameter extraction and scientific guidance for forest resource investigation and forest management decision-making.

Floristic Diversity and Natural Regeneration of Miombo Woodlands in the Rural Area of Lubumbashi, D.R. Congo

Increased anthropogenic pressure on forest resources leads to deforestation and forest degradation, significantly limiting the regeneration capacity of native woody species and consequently the restoration of miombo woodlands in anthropized habitats within the rural area of Lubumbashi. This study assessed miombo species’ diversity and natural regeneration capacity through floristic inventories in three different habitats (unexploited forests, degraded forests, and post-cultivation fallows). The results reveal that for the adult stratum, unexploited and degraded forests exhibit higher dendrometric (density, mean square diameter, basal area) and floristic parameter (taxa, genera, families) values compared to post-cultivation fallows. Furthermore, the regeneration of miombo woody species is higher in degraded forests (21 taxa; 105 juveniles/plot). However, regarding the sapling’s stratum (1 cm ≤ dbh < 10 cm), the three habitats display similar situations. Additionally, the floristic composition and diversity of unexploited and degraded forests show a significantly higher similarity (76.50%) among them compared to these habitats and the post-cultivation fallows (56.00%). These findings indicate that miombo woodlands have the potential to regenerate and maintain floristic diversity even in anthropized habitats, particularly in degraded forests. To sustain this natural regeneration capacity of miombo woody species and promote the restoration of forest cover and its floristic diversity, it is imperative to determine the rotation period after habitat exploitation and regulate anthropogenic activities and late bush fires, particularly in anthropized habitats at the village level.

Research Trends in Wildland Fire Prediction Amidst Climate Change: A Comprehensive Bibliometric Analysis

Wildfire prediction plays a vital role in the management and conservation of forest ecosystems. By providing detailed risk assessments, it contributes to the reduction of fire frequency and severity, safeguards forest resources, supports ecological stability, and ensures human safety. This study systematically reviews wildfire prediction literature from 2003 to 2023, emphasizing research trends and collaborative trends. Our findings reveal a significant increase in research activity between 2019 and 2023, primarily driven by the United States Forest Service and the Chinese Academy of Sciences. The majority of this research was published in prominent journals such as the International Journal of Wildland Fire, Forest Ecology and Management, Remote Sensing, and Forests. These publications predominantly originate from Europe, the United States, and China. Since 2020, there has been substantial growth in the application of machine learning techniques in predicting forest fires, particularly in estimating fire occurrence probabilities, simulating fire spread, and projecting post-fire environmental impacts. Advanced algorithms, including deep learning and ensemble learning, have shown superior accuracy, suggesting promising directions for future research. Additionally, the integration of machine learning with cellular automata has markedly improved the simulation of fire behavior, enhancing both efficiency and precision. The profound impact of climate change on wildfire prediction also necessitates the inclusion of extensive climate data in predictive models. Beyond conventional studies focusing on fire behavior and occurrence probabilities, forecasting the environmental and ecological consequences of fires has become integral to forest fire management and vital for formulating more effective wildfire strategies. The study concludes that significant regional disparities in knowledge exist, underscoring the need for improved research capabilities in underrepresented areas. Moreover, there is an urgent requirement to enhance the application of artificial intelligence algorithms, such as machine learning, deep learning, and ensemble learning, and to intensify efforts in identifying and leveraging various wildfire drivers to refine prediction accuracy. The insights generated from this field will profoundly augment our understanding of wildfire prediction, assisting policymakers and practitioners in managing forest resources more sustainably and averting future wildfire calamities.

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.

Using Multi-Source National Forest Inventory Data for the Prediction of Tree Lists of Individual Stands for Long-Term Simulation

Forest resource maps and small area estimates have been produced by combining national forest inventory (NFI) field plot data, multispectral satellite images and numerical map data. We evaluated k-nearest neighbors (k-NN) method-based predictions of forest variables for pixels in predicting tree lists of individual stands, including tree diameters at breast height and tree heights and then calculated stem volumes and tree species proportions. We compared alternative parameters (k-NN) using k of either 1 or 5 according to preliminary plot-level study and applying either measured trees (1-NN_trees) or mean stand characteristics (k-NN_stand). In the 1-NN_trees method, a tree list was generated based on the measured trees of the NFI plots, whereas in the 1-NN_stand and 5-NN_stand methods, a Weibull-based diameter distribution was recovered from the stand characteristics of the same inventory plots. In both methods, tree lists were predicted for each 16 m × 16 m pixel included in the stand compartment. Both methods performed well and resulted in 8–14% differences in the total volume compared with the field inventory of the 27 stands used for the evaluation. Moreover, the main tree species was correctly predicted for 74% of cases. The RMSE in total volume ranged from 25% (5-NN_stand) to 31% (1-NN_stand), while the smallest RMSEs in volume by tree species were 61% for broadleaves and 65% for pine and spruce using the 5-NN_stand. When comparing input data for a long-term growth simulation, the choice of the method was less influential as the effect of the error in the initial stand characteristics decreased over time during the simulation period. After 30-year simulation of the inventoried stands, the respective RMSEs were 9.4% for total volume and 39%, 50% and 59% for tree species, respectively. The satellite-based data with NFI plots were useful for predicting tree lists for pixels of a stand. However, the accuracy for operational forest management was still questionable. For a larger area’s strategic information, the accuracy is considered adequate.

Evaluating machine learning approaches for aboveground biomass prediction in fragmented high-elevated forests using multi-sensor satellite data

Accurate aboveground biomass (AGB) estimations over large areas are essential for assessing carbon stocks and forest resources. This study evaluated machine learning approaches for AGB modeling in Pakistan's mountainous region of Diamir district using freely available Sentinel-1 and Sentinel-2 data and 171 field-measured AGB training points. Random Forest, Gradient Tree Boosting, CatBoost, LightGBM, and XGBoost algorithms were implemented and optimized. Models were developed using individual and combined datasets. Sentinel-2 optical data outperformed Sentinel-1 radar data, but the fusion of both sensors achieved the highest accuracy (R2 > 0.7, RMSE = 105.64 Mg/ha, MAE = 85.34 Mg/ha). Tree canopy height was the most informative predictor for this data, besides terrain variables and radar textures. The machine learning models significantly improved AGB estimates compared to traditional regression techniques, and gradient boosters outperformed Random Forest. This research demonstrates the potential of multi-sensor remote sensing data and advanced algorithms for forest biomass mapping in complex terrain, with modeling accuracies reaching root mean squared errors below 90 Mg/ha. The framework provides an effective solution for monitoring biomass using freely available satellite data. Further refinements include integrating higher-resolution optical data and additional field samples for better validation. This study contributes to remote sensing capabilities for assessing vegetation carbon stocks and dynamics.