Forest Type Classification Research Articles

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model’s classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development.

Different Approaches of Forest Type Classifications for Argentina Based on Functional Forests and Canopy Cover Composition by Tree Species

Modern forestry systems rely on typologies of forest types (FTs). In Argentina, several proposals have been developed, but they lack unified criteria. The objective was to compare different approaches, specifically focusing on (i) phenoclusters (functional forests based on vegetation phenology variations and climate variables) and (ii) forest canopy cover composition by tree species. We conducted comparative uni-variate analyses using data from national forest inventories, forest models (biodiversity, carbon, structure), and regional climate. We assessed the performance of phenoclusters in differentiating the variability of native forests (proxy: forest structure), biodiversity (proxy: indicator species), and environmental factors (proxies: soil carbon stock, elevation, climate). Additionally, we proposed a simple FT classification methodology based on species composition, considering the basal area of tree species. Finally, we compared the performance of both proposals. Our findings showed that classifications based on forest canopy cover composition are feasible to implement in regions dominated by mono-specific forests. However, phenoclusters allowed for the increased complexity of categories at the landscape level. Conversely, in regions where multi-specific stands prevailed, classifications based on forest canopy cover composition proved ineffective; however, phenoclusters facilitated a reduction in complexity at the landscape level. These results offer a pathway to harmonize national FT classifications by employing criteria and indicators to achieve sustainable forest management and conservation initiatives.

Integration of Unmanned Aerial Vehicle Imagery and Machine Learning Technology to Map the Distribution of Conifer and Broadleaf Canopy Cover in Uneven-Aged Mixed Forests

Uneven-aged mixed forests have been recognized as important contributors to biodiversity conservation, ecological stability, carbon sequestration, the provisioning of ecosystem services, and sustainable timber production. Recently, numerous studies have demonstrated the applicability of integrating remote sensing datasets with machine learning for forest management purposes, such as forest type classification and the identification of individual trees. However, studies focusing on the integration of unmanned aerial vehicle (UAV) datasets with machine learning for mapping of tree species groups in uneven-aged mixed forests remain limited. Thus, this study explored the feasibility of integrating UAV imagery with semantic segmentation-based machine learning classification algorithms to describe conifer and broadleaf species canopies in uneven-aged mixed forests. The study was conducted in two sub-compartments of the University of Tokyo Hokkaido Forest in northern Japan. We analyzed UAV images using the semantic-segmentation based U-Net and random forest (RF) classification models. The results indicate that the integration of UAV imagery with the U-Net model generated reliable conifer and broadleaf canopy cover classification maps in both sub-compartments, while the RF model often failed to distinguish conifer crowns. Moreover, our findings demonstrate the potential of this method to detect dominant tree species groups in uneven-aged mixed forests.

Classification and nomenclature of temperate forest types in Mexico

Aims: To analyze and synthesize the principal contributions to the creation of a classification of established forests in sub-humid, temperate climatic regions in Mexico. Methods: Documentary analysis and review of works on the classification of the vegetation of Mexico, with emphasis from 1950 to the present. To identify and analyze the terms frequently used to refer to these plant communities, the following was done: literature search, analysis of frequencies and co-occurrences of these terms that appeared in the titles of the documents. A list of associations of these communities was compiled through a documentary review. Results: Vegetation classification proposals, both nationally and internationally, tend towards the standardization of criteria and nested hierarchical integration at various levels based on physiognomic, climatic, phenological and floristic attributes. The two highest levels of organization in these proposals are based on major vegetation, defined by vegetation forms and climatic criteria as “temperate forests”. Meanwhile lower levels, including the level of associations, are based on their floristic composition. The most frequently used term to refer to these plant communities, according to the documents used in the search, is “temperate forest”, although other terms frequently used are “coniferous forest”, “pine forest”, and “oak forest”. Conclusions: Knowledge about the classification of vegetation in Mexico dates back to pre-Hispanic times. However, it was not until the second half of the 20th century that solid proposals that are influential today were put forward. Given the high biological diversity of the country, it is still a pending task to characterize and make an inventory of the diversity at the level of associations that form this type of temperate forests. Taxonomic reference: Villaseñor (2016). Abbreviations: FVT = Trans-Mexican Volcanic Belt; SECLAVEMEX = Mexican Vegetation Classification System; SMO = Sierra Madre Oriental; SMOc = Sierra Madre Occidental; SMS = Sierra Madre del Sur (SMS).

Лесные типологии в Российской Федерации

The aim of the work is to conduct a comparative analysis of the main Russian forest type classifications: forest-ecological classification by E.V. Alekseev – P.S. Pogrebnyak, phytocoenotic classification by V.N. Sukachev, genetic classification by B.A. Ivashkevich – B.P. Kolesnikov and dynamic one by I.S. Melekhov. The comparison is made on the following positions: the content of the concept of classification unit (type of habitat conditions, forest type); peculiarities of the classification unit boundary; classification features for determining the type of habitat conditions; distinctive features of phytocenosis classification for establishing the forest type; the degree of consideration of successional dynamics of forest plantations and the influence of anthropogenic factors; the level of implementation in forestry practice and regions of implementation. It is established that during the development of forest typologies the idea of forest type changed from a forest area that is homogeneous in composition, structure and appearance (homogeneity in space) in natural classifications to the idea of forest type with the priority of homogeneity in origin (genesis), development processes and dynamics (homogeneity in time) in comparison with the homogeneity of composition and structure in genetic and dynamic typologies. The geographical distribution of forest-ecological, phytocenotic and genetic classifications of forest types in the Russian Federation at the present moment is given. Forest-ecological classifications are used mainly in the southern regions of the European Russia and in the North Caucasus. Forest typologies based on the genetic approach to forest type classification are used in Western Siberia, in the south of the Far East and Eastern Siberia, and in some regions of the Urals. In the rest of the Russian Federation, phytocenotic classifications of forest types are used. The unification of existing typologies into a single classification is possible on the basis of the genetic approach, as natural typologies within the framework of this approach can be a component of genetic classifications. The solution of the problem of combining the use of different typologies in one region will provide the level of forest inventory, allowing to optimize forest management and compare the obtained data both for the subjects of the Russian Federation and for the country as a whole. For citation: Fomin V.V., Ivanova N.S., Zalesov S.V., Popov A.S., Mikhailovich A.P. Forest Typologies in the Russian Federation. Lesnoy Zhurnal = Russian Forestry Journal, 2023, no. 6, pp. 9–30. (In Russ.). https://doi.org/10.37482/0536-1036-2023-6-9-30

Динамика экосистем свежего бора центра Приволжской возвышенности

The results of a study of the dynamics of a rather rare type of forest ecosystem for the central part of the Volga Upland – fresh pinery (A2) – are presented. The research was carried out on the territory of the Upper Sura section of the Volga Forest-Steppe Nature Reserve. The progress of the process was studied in an age series, identified in homogeneous forest conditions based on the principles of dynamic classification of forest types. As a result of processing forest taxation data, average values of taxation indicators of forest stands were obtained for each age class. At the same time, an analysis of changes in all components of the plantings was carried out. On its basis, the age series was divided into separate periods and phases. Trends in the share of participation of each forest-forming species in the forest stand at different age stages are described by nonlinear equations. The study showed that the resulting age series represents a series of transformation of forest communities. Disruption of the forest formation process led to a large-scale replacement of indigenous plantings with derivatives. After the start of clear-cutting, the area occupied by deciduous trees (primarily birch) constantly grew. A consequence of the large-scale use of intermediate, sanitary and voluntary selective fellings was the formation of thinned pine stands. At the same time, a transformation of the lower tiers of communities also occurred. These factors caused a deterioration in the conditions for natural regeneration of pine (Pinus sylvestris L.). As a result, to date, the possibility of forming pine stands through natural regeneration is almost completely excluded.

Mountain Forest Type Classification Based on One-Dimensional Convolutional Neural Network

Convolutional neural networks (CNNs) have demonstrated their efficacy in remote sensing applications for mountain forest classification. However, two-dimensional convolutional neural networks (2D CNNs) require a significant manual involvement in the visual interpretation to obtain continuous polygon label data. To reduce the errors associated with manual visual interpretation and enhance classification efficiency, it is imperative to explore alternative approaches. In this research, we introduce a novel one-dimensional convolutional neural network (1D CNN) methodology that directly leverages field investigation data as labels for classifying mountain forest types based on multiple remote sensing data sources. The hyperparameters were optimised using an orthogonal table, and the model’s performance was evaluated on Mount Emei of Sichuan Province. Comparative assessments with traditional classification methods, namely, a random forest (RF) and a support vector machine (SVM), revealed superior results obtained by the proposed 1D CNN. Forest type classification using the 1D CNN achieved an impressive overall accuracy (OA) of 97.41% and a kappa coefficient (Kappa) of 0.9673, outperforming the U-Net (OA: 94.45%, Kappa: 0.9239), RF (OA: 88.99%, Kappa: 0.8488), and SVM (OA: 88.79%, Kappa: 0.8476). Moreover, the 1D CNN model was retrained using limited field investigation data from Mount Wawu in Sichuan Province and successfully classified forest types in that region, thereby demonstrating its spatial-scale transferability with an OA of 90.86% and a Kappa of 0.8879. These findings underscore the effectiveness of the proposed 1D CNN in utilising multiple remote sensing data sources for accurate mountain forest type classification. In summary, the introduced 1D CNN presents a novel, efficient, and reliable method for mountain forest type classification, offering substantial contributions to the field.

Relationships among livestock, structure, and regeneration in Chilean Austral Macrozone temperate forests

A Macrozone is a socioecological region with shared geographic and demographic characteristics. Within the Chilean Austral Macrozone (43° to 56° SL), the native temperate forests serve as a crucial resource, offering multiple ecosystem services to local communities. These forests significantly support animal husbandry practices involving cattle, horses and sheep. However, introducing these exotic species affects natural regeneration and compromises their long-term sustainability. This study proposes a new classification of the temperate forests in the Chilean Austral Macrozone based on structure parameters and determine their relationships with animal husbandry and natural regeneration. Data were obtained from Chile's National Forest Inventory (NFI) (2001–2010), including 195 inventory plots (500 m2) with 21 tree species. We redefined the forest categories described in NFI according to the proportional basal area of each tree species at each plot. We used two levels of analysis: forest composition (Level 1), which includes general categories such as mono-specific (dominated by a single tree species), bi-specific (dominated by two tree species), and multi-specific forests (dominated by multiple tree species), and forest type (Level 2), which includes specific species (e.g., Nothofagus pumilio) or species groups (e.g., N. pumilio - N. dombeyi) with economic relevance. We evaluated the data using univariate and multivariate analyses. We found 18 forest types in the Austral Macrozone, in contrast to the three traditionally recognized forest types used in the NFI (e.g., lenga, evergreen, coihue de Magallanes). Livestock was observed in all forest types, where Nothofagus forests showed that regeneration in N. antarctica and N. pumilio were higher with livestock than without livestock breeding (Hedges' g > 0.51). The natural regeneration of the studied forests was influenced by animal husbandry, environmental variables (bioclimatic and topographic factors), and forest structure. Our data suggested the importance of using more forest types than the three classics to generate tools or recommendations that are more focused on the particularities of each one. The classification must be based on forest parameters obtained during NFI. The proposed forest type classification reflects the complexity and richness of the forests in a better way, which could improve forest management and the development of public policies related to climate change and sustainability. Finally, although livestock pressure was observed in all forest types, the impact over some areas (e.g., N. antarctica) needs special attention in the forest management and conservation planning for the Chilean Austral Macrozone.

Seasonality and directionality effects on radar backscatter are key to identify mountain forest types with Sentinel-1 data

Systematic Sentinel-1 acquisitions provide an unprecedented stream of SAR data which allows to describe forest temporal dynamics in detail, a powerful tool for phenological studies and forest type classification. Several studies have explored the temporal variation of backscatter intensity in this context, but none considered that scattering directionality of canopies may vary. Said directionality is related to target-sensor geometry (incidence angle), forest height, and optical depth, associated with leaf dynamics. This study explicitly models backscatter dependance on incidence angle by fitting a regression model for each Sentinel-1 image and forest type. Residuals are accumulated across the time series and used to classify pixels into the most likely forest type using the smallest accumulated residual. This modelling and classification strategy has been applied over a North-South transect across the Carpathian Mountains, including forests with different physiognomies, from deciduous broadleaf forest, to mixed broadleaf-needleleaf and pure perennial needleleaf forests. These forests were classified with increasing detail, assessing the results against in-situ forest stand data and satellite-based land cover classification products (Copernicus Forest type layer). The accuracy of our classification was K > 0.8, OA > 90% when separating broadleaf from needleleaf forest types. The accuracy decreased (K > 0.6, OA > 79%) when also separating mixed forest types. Our results suggest that incorporating directional effects into classification models can improve SAR-based forest classification of temperate forest over mountainous terrain. Furthermore, models fitted between backscatter and incidence angle provide an estimate of n, a parameter related to optical depth that has been shown to vary with leaf dynamics. ncould be used to improve image normalization in studies aiming at the estimation of biomass, or to aid the estimation of fast-changing parameters such as leaf area index or leaf moisture content.

A Scalable AI Training Platform for Remote Sensing Data

Abstract. We present a platform to support the AI development lifecycle with focus on large data like remote sensing.We target developers who are not allowed to use existing commercial cloud platforms for legal reasons or data compliance. The flexible implementation of our platform enables a deployment on classic server infrastructures as well as on internal clouds. Our goals of scalable and resource-efficient execution, independence from specific AI frameworks and programming languages, as well as reproducibility of results are met through a workflow-based calculation combined with the tool Data Version Control. The capabilities of the platform are demonstrated by training an AI-based forest type classification.

Estimating the Forest Carbon Storage of Chongming Eco-Island, China, Using Multisource Remotely Sensed Data

Urban forests are highly heterogeneous; information about the combined effect of forest classification scale and algorithm selection on the estimation accuracy for urban forests remains unclear. In this study, we chose Chongming eco-island in the mega-city of Shanghai, a national experimental carbon neutral construction plot in China, as the study object. Remote sensing estimation models (simple regression models vs. machine learning models) of forest carbon density were constructed across different classification scales (all forests, different forest types, and dominant tree species) based on high-resolution aerial photographs and Sentinel-2A remote sensing images, and a large number of field surveys and optimal models were screened by ten-fold cross-validation. The results showed that (1) in early 2020, the total forest area and carbon storage of Chongming eco-island were 307.8 km2 and 573,123.6 t, respectively, among which the areal ratios and total carbon storage ratios of evergreen broad-leaved forest, deciduous broad-leaved forest, and warm coniferous forest were 51.4% and 53.3%, 33.5% and 32.8%, and 15.1% and 13.9%, respectively. (2) The average forest carbon density of Chongming eco-island was 18.6 t/ha, among which no differences were detected among the three forest types (i.e., 17.2–19.2 t/ha), opposite to what was observed among the dominant tree species (i.e., 14.6–23.7 t/ha). (3) Compared to simple regression models, machine learning models showed an improvement in accuracy performance across all three classification scales, with average rRMSE and rBias values decreasing by 29.4% and 53.1%, respectively; compared to the all-forests classification scale, the average rRMSE and rBias across the algorithms decreased by 25.0% and 45.2% at the forest-type classification scale and by 28.6% and 44.3% at the tree species classification scale, respectively. We concluded that refining the forest classification, combined with advanced prediction procedures, could improve the accuracy of carbon storage estimates for urban forests.

Application of a Novel Multiscale Global Graph Convolutional Neural Network to Improve the Accuracy of Forest Type Classification Using Aerial Photographs

The accurate classification of forest types is critical for sustainable forest management. In this study, a novel multiscale global graph convolutional neural network (MSG-GCN) was compared with random forest (RF), U-Net, and U-Net++ models in terms of the classification of natural mixed forest (NMX), natural broadleaved forest (NBL), and conifer plantation (CP) using very high-resolution aerial photographs from the University of Tokyo Chiba Forest in central Japan. Our MSG-GCN architecture is novel in the following respects: The convolutional kernel scale of the encoder is unlike those of other models; local attention replaces the conventional U-Net++ skip connection; a multiscale graph convolutional neural block is embedded into the end layer of the encoder module; and various decoding layers are spliced to preserve high- and low-level feature information and to improve the decision capacity for boundary cells. The MSG-GCN achieved higher classification accuracy than other state-of-the-art (SOTA) methods. The classification accuracy in terms of NMX was lower compared with NBL and CP. The RF method produced severe salt-and-pepper noise. The U-Net and U-Net++ methods frequently produced error patches and the edges between different forest types were rough and blurred. In contrast, the MSG-GCN method had fewer misclassification patches and showed clear edges between different forest types. Most areas misclassified by MSG-GCN were on edges, while misclassification patches were randomly distributed in internal areas for U-Net and U-Net++. We made full use of artificial intelligence and very high-resolution remote sensing data to create accurate maps to aid forest management and facilitate efficient and accurate forest resource inventory taking in Japan.

Combining Environmental, Multispectral, and LiDAR Data Improves Forest Type Classification: A Case Study on Mapping Cool Temperate Rainforests and Mixed Forests

Predictive vegetation mapping is an essential tool for managing and conserving high conservation-value forests. Cool temperate rainforests (Rainforest) and cool temperate mixed forests (Mixed Forest, i.e., rainforest spp. overtopped by large remnant Eucalyptus trees) are threatened forest types in the Central Highlands of Victoria. Logging of these forest types is prohibited; however, the surrounding native Eucalyptus forests can be logged in some areas of the landscape. This requires accurate mapping and delineation of these vegetation types. In this study, we combine niche modelling, multispectral imagery, and LiDAR data to improve predictive vegetation mapping of these two threatened ecosystems in southeast Australia. We used a dataset of 1586 plots partitioned into four distinct forest types that occur in close proximity in the Central Highlands: Eucalyptus, Tree fern, Mixed Forest, and Rainforest. We calibrated our model on a training dataset and validated it on a spatially distinct testing dataset. To avoid overfitting, we used Bayesian regularized multinomial regression to relate predictors to our four forest types. We found that multispectral predictors were able to distinguish Rainforest from Eucalyptus forests due to differences in their spectral signatures. LiDAR-derived predictors were effective at discriminating Mixed Forest from Rainforest based on forest structure, particularly LiDAR predictors based on existing domain knowledge of the system. For example, the best predictor of Mixed Forest was the presence of Rainforest-type understorey overtopped by large Eucalyptus crowns, which is effectively aligned with the regulatory definition of Mixed Forest. Environmental predictors improved model performance marginally, but helped discriminate riparian forests from Rainforest. However, the best model for classifying forest types was the model that included all three classes of predictors (i.e., spectral, structural, and environmental). Using multiple data sources with differing strengths improved classification accuracy and successfully predicted the identity of 88% of the plots. Our study demonstrated that multi-source methods are important for capturing different properties of the data that discriminate ecosystems. In addition, the multi-source approach facilitated adding custom metrics based on domain knowledge which in turn improved the mapping of high conservation-value forest.

YURI IVANOVICH MANKO – A LIFE DEDICATED TO THE FOREST

An article about the famous Far Eastern forester, Doctor of Biological Sciences, Professor, Honored Forester of Russia Yuri Ivanovich Manko (25.11.1931 – 19.02.2021). After graduating from the Siberian Forestry Institute in 1954, he was assigned to the Far Eastern branch of the SB Academy of Sciences of the USSR named after V.L. Komarov and taken to the Department of Botany and Plant Science in the Laboratory of Forestry, which was organized and headed by Professor Boris Pavlovich Kolesnikov. In 1966, already as part of the Biology and Soil Sience Institute, established in 1962, the laboratory was reorganized into a non-structural forest Department. In 1962, Yu.I. Manko defended his Candidate thesis «Natural regeneration of fir-spruce forests of the northern half of Sikhote-Alin and some issues of their structure and development», in 1985 – his doctoral dissertation «Ayan spruce (distribution, biology, classification of forest types, features of age structure and dynamics of phytocenoses». The scientific heritage of Yuri Ivanovich exceeds 330 publications on forestry, botany, soil science, botanical geography, history of science, nature conservation issues. Yuri Ivanovich Manko throughout his scientific activity developed and promoted the «genetic» or «geographical-genetic» direction of forest typology closely related to the forest formation process, which was developed on the basis of the scientific heritage of B.A. Ivashkevich-B.P. Kolesnikov. He supplemented the theory of the forest formation process by characterizing the zonal features of this process in the area of the Ayan spruce with autogenous vegetation development and exogenous destructive effects. They were shown that the spectrum of particular forest-forming processes is specific for various sub-formations and geographical facies, and their dynamics depends on geomorphological conditions and the speed of modern reliefforming processes. The name of Yuri Ivanovich Manko is inscribed in the history of Far Eastern science as an outstanding researcher of forests.

Dynamics of ecosystems of fresh subor (pine woods on sandy soils) in the central part of the Volga Upland

The results of our study of the dynamics of fresh subor (B2), a widespread type of forest ecosystems in the central part of the Volga Upland, are presented. The study was carried out on the territory of the Upper Sura section of the Privolzhskaya Forest-Steppe Nature Reserve. The course of the process was studied in the age series identified in homogeneous forest conditions based on the principles of dynamic classification of forest types. As a result of processing the forest inventory data, the average values of forest stand taxation indicators were obtained for each age class. At the same time, analysis of changes in all the components of plantations was carried out. On its basis, the age series was divided into separate periods and phases. Trends in the share of participation of each forest-forming species in the forest stand at different age stages were described by nonlinear equations. The study showed the resulting age series to be a series of transformation of forest communities. Violation of the course of the forest formation process led to a large-scale change of indigenous plantations to derivative ones. After the beginning of the use of clear-cutting fellings, the area occupied by deciduous trees (primarily birch) has been constantly growing. The largescale use of intermediate-use, sanitary and voluntary-selective cuttings resulted in the formation of sparse pine stands. At the same time, transformation of the lower tiers of communities took place. These factors caused deterioration of the conditions for natural pine regeneration (Pinus sylvestris L.). As a result, by now the possibility of forming pine forest stands through natural regeneration is almost completely excluded.

Comparison of methods for the automatic classification of forest habitat types in the Southern Alps—Application to ecological data from the French national forest inventory

Comparison of methods for the automatic classification of forest habitat types in the Southern Alps—Application to ecological data from the French national forest inventory

On the Ways of Forest Typology Researches in Siberia in the 1960s–2000s

The article presents a brief overview of the works on forest typology and zoning of Siberia conducted at the Forest Typology Laboratory of the Institute of Forest and Timber of the USSR Academy of Sciences, later Sukachev Institute of Forest of the Siberian Branch of the Russian Academy of Sciences. The ecological and phytocoenotic line of research and the regional approach to the creation of diagnostic tables of forest types were adopted as a basis for complex field work carried out jointly with forest management throughout Siberia. The principal features of forest typological work in mountains required the improvement of the system of classification units and mapping of forest cover with determining their diagnostic indicators. The significance of these works for the development of the concept of systemic structure of forest cover and its deep connection with the concept of hierarchical structure of landscape cover through the idea of biogeocenosis and terrestrial ecosystem are meaningful for today. The author speaks in favor of the regional approach to classification of forest types but does not close the way to the creation of a generalized classification of forest ecosystems based on climatic ordination and information modeling. The practical use of ecological-phytocenotic regional classifications of forest cover is substantiated for creating medium-scale maps for various purposes and solving environmental management problems, with the access to ecosystem management of forest territories.

Impacts of Japanese Larch Invasion on Soil Bacterial Communities of the Giant Panda Habitat in the Qinling Mountains

Japanese larch (Larix kaempferi), a non-native tree species, has been widely planted in the Qinling Mountains since the last century, but it does not meet the habitat needs of giant pandas (Ailuropoda melanoleuca), mainly because of food, further causing habitat degradation and fragmentation. However, how soil microorganisms, considered as predictors of the soil environment, respond to Japanese larch remains poorly explored, especially compared with native forests. Here, we collected 40 soil samples from plantation, bamboo, and natural (excluding bamboo) forests in the Changqing Nature Reserve and Foping Nature Reserve in Qinling to compare soil bacterial community composition and diversity using high-throughput sequencing of bacterial 16S rRNA genes. The soil chemical properties and bacterial communities differed noticeably under forest-type classification patterns. The soil of the Japanese larch planted forests underwent substantial degradation, with higher acidity, lower alpha diversity, and more significant enrichment in the oligotrophic bacteria Acidobacteria and Verrucomicrobia, in contrast to the other two primary forests with elevated soil nutrient levels. The application of PICRUSt2 indicated the down-regulation of amino acid-related metabolism in planted forests. Moreover, pH was the primary factor determining the whole bacterial community structures. To avoid the uncertainty of a single sampling region, we chose different sampling sites that could be considered as geographical factors, possibly due to environmental heterogeneity or dispersal limitations, which also explained the specific community patterns of microorganisms. Overall, this paper may help provide a scientific basis for future revegetation in giant panda habitats, highlighting the urgent need for ecological restoration and sustainable forestry management.

Classification of forest types in Cuigang Forest Farm based on time series data of Landsat 8

To explore the practical role of enhanced vegetation index (EVI) time series data in improving the accuracy of forest type recognition could promote the deep application of optical remote sensing data in forest resources investigation and monitoring. With Cuigang Forest Farm of Xinlin Forestry Bureau in Daxing'anling as the object, we constructed six classification schemes, using random forest algorithm with spectral feature, texture feature and EVI time series feature. The data sources were 20-view Landsat 8 OLI time series data from 2014 to 2018, 56 fixed plots data from 2017-2019, and the 2016 Class II survey data. Our aims were to realize the classification of forest types in Cuigang Forest Farm and to evaluate the accuracy of different classification schemes. The results showed the EVI values of Larix gmelinii forest, Betula platyphylla forest, coniferous-broadleaved mixed forest, coniferous mixed forest and broadleaved mixed forest were significantly different in non-growing seasons (36-111 days and 287-367 days), with the EVI value of mixed conifer forest being significantly higher, and that of mixed broadleaf forest being always lower than the other four forest types. In the early growing season (111-143 days), the EVI value of B. platyphylla forest were higher than L. gmelinii forest, which could effectively distinguish the two forests. Among the six classification schemes, spectral feature, texture feature, and EVI time series feature had the highest classification accuracy, with a Kappa of 0.82 and a classification accuracy of 86.1%. The comparison results showed that the overall accuracy of adding vegetation index time series feature was improved by 14.3% compared with that of spectral feature. The random forest algorithm with combined spectral, texture and EVI time series features could effectively classify forest stand types in Cuigang Forest Farm, with good recognition accuracy and confidence.

The Classification of Forest Types in Deciduous Forests Using the National Forest Inventory Data

The Classification of Forest Types in Deciduous Forests Using the National Forest Inventory Data