Small-scale Maps Research Articles

Multi-Robot Collaborative Mapping with Integrated Point-Line Features for Visual SLAM.

Simultaneous Localization and Mapping (SLAM) enables mobile robots to autonomously perform localization and mapping tasks in unknown environments. Despite significant progress achieved by visual SLAM systems in ideal conditions, relying solely on a single robot and point features for mapping in large-scale indoor environments with weak-texture structures can affect mapping efficiency and accuracy. Therefore, this paper proposes a multi-robot collaborative mapping method based on point-line fusion to address this issue. This method is designed for indoor environments with weak-texture structures for localization and mapping. The feature-extraction algorithm, which combines point and line features, supplements the existing environment point feature-extraction method by introducing a line feature-extraction step. This integration ensures the accuracy of visual odometry estimation in scenes with pronounced weak-texture structure features. For relatively large indoor scenes, a scene-recognition-based map-fusion method is proposed in this paper to enhance mapping efficiency. This method relies on visual bag of words to determine overlapping areas in the scene, while also proposing a keyframe-extraction method based on photogrammetry to improve the algorithm's robustness. By combining the Perspective-3-Point (P3P) algorithm and Bundle Adjustment (BA) algorithm, the relative pose-transformation relationships of multi-robots in overlapping scenes are resolved, and map fusion is performed based on these relative pose relationships. We evaluated our algorithm on public datasets and a mobile robot platform. The experimental results demonstrate that the proposed algorithm exhibits higher robustness and mapping accuracy. It shows significant effectiveness in handling mapping in scenarios with weak texture and structure, as well as in small-scale map fusion.

The use of graph convolutional networks in road selection for small-scale maps design

The use of graph convolutional networks in road selection for small-scale maps design

Copying-lineages of portolan chart metrics and implications of their pre-medieval origin

ABSTRACT Seven portolan charts and atlases (including the anonymous Rex Tholomeus chart) made between 1311 and 1538 were cartometrically analysed. The findings indicate that their geometry was not improved chronologically and that the accuracy of Pietro Vesconte's charts (1311–13) was never surpassed. Portolan charts and atlases appear to be mosaics composed of subsections, each with variable metrics and accuracy levels that are, on average, twice as great in comparison to their Mediterranean and Black Sea areas (as a whole), and it is highly unlikely that they are genuine late medieval products, which is also supported by historical evidence. Their anticlockwise tilts fit well with the tilt of the Gibraltar-Antioch line on modern maps that closely approximate Ptolemy I and Ptolemy II projections centred near Gibraltar and with their meridian tilts for areas around Genoa. If late medieval Italian cartographers had acquired a collection of maps or charts from before the Middle Ages, it is theoretically feasible that they could have achieved the typical geometry of portolan charts by graphically combining their manuscript copies of large-scale regional maps in Mercator or Mercator-like projection, using a small-scale map in conic or pseudoconic projection (on which the convergence of meridians is displayed) as a template.

Effect of surficial geology mapping scale on modelled ground ice in Canadian Shield terrain

Abstract. Ground ice maps at small scales offer generalized depictions of abundance across broad circumpolar regions. In this paper, the effect of surficial geology mapping scale on modelled ground ice abundance is examined in the Slave Geological Province of the Canadian Shield, a region where the geological and glacial legacy has produced a landscape with significant variation in surface cover. Existing model routines from the Ground ice map of Canada (GIMC) were used with a 1:125 000-scale regional surficial geology compilation and compared to the national outputs, which are based on surficial geology at a 1:5 000 000 scale. Overall, the regional-scale modelling predicts much more ground ice than the GIMC due to greater representation of unconsolidated sediments in the region. Improved modelling accuracy is indicated by comparison of the outputs to empirical datasets due to improved representation of the inherent regional heterogeneity in surficial geology. The results demonstrate that the GIMC significantly underestimates the abundance and distribution of ground ice over Canadian Shield terrain. In areas with limited information on ground ice, regional-scale modelling may provide useful reconnaissance-level information to help guide the field-based investigations required for planning infrastructure development. The use of current small-scale ground ice mapping in risk or cost assessments related to permafrost thaw may significantly influence the accuracy of outputs in areas like the Canadian Shield, where surficial materials range from bedrock to frost-susceptible deposits over relatively short distances.

SUITABILITY AND CHALLENGES OF OPEN MAPS FOR EUROPE DATA FOR CREATING A GENERAL PURPOSE SMALL-SCALE MAP OF CROATIA

Abstract. The adoption of the Open Data Directive in 2019 compelled the launch of the Open Maps for Europe project, aiming to provide accessible and harmonized geospatial data from over 40 European countries. This research investigates the suitability of Open Maps for Europe data for creating a general purpose small-scale map of Croatia. The study applies digital cartographic procedures to produce the map, while assessing data quality and fitness for this task. The methodology for map creation involved seven key steps: (1) extracting data from the 1:250,000 scale EuroRegionalMap dataset, (2) performing geometric, topological, and attribute conversions, (3) applying cartographic generalization to adapt the map content to a 1:500,000 scale, (4) conducting data quality checks, (5) addressing exceptions, (6) symbolizing and placing names, and (7) designing a printable map. The resulting general-purpose map of Croatia at a 1:500 000 scale demonstrates that Open Maps for Europe data is generally suitable for map creation at this scale. However, challenges such as data heterogeneity among countries, data gaps in certain areas, inappropriate levels of generalization, and disordered geometry may arise. The map created should be considered an intermediate, rather than a reliable and trustworthy final product since rigorous quality control measures should be undertaken to produce the final map.

SiameseNet Based Fine-Grained Semantic Change Detection for High Resolution Remote Sensing Images

Change detection in high resolution (HR) remote sensing images faces more challenges than in low resolution images because of the variations of land features, which prompts this research on faster and more accurate change detection methods. We propose a pixel-level semantic change detection method to solve the fine-grained semantic change detection for HR remote sensing image pairs, which takes one lightweight semantic segmentation network (LightNet), using the parameter-sharing SiameseNet, as the architecture to carry out pixel-level semantic segmentations for the dual-temporal image pairs and achieve pixel-level change detection based directly on semantic comparison. LightNet consists of four long–short branches, each including lightweight dilated residual blocks and an information enhancement module. The feature information is transmitted, fused, and enhanced among the four branches, where two large-scale feature maps are fused and then enhanced via the channel information enhancement module. The two small-scale feature maps are fused and then enhanced via a spatial information enhancement module, and the four upsampling feature maps are finally concatenated to form the input of the Softmax. We used high resolution remote sensing images of Lake Erhai in Yunnan Province in China, collected by GF-2, to make one dataset with a fine-grained semantic label and a dual-temporal image-pair label to train our model, and the experiments demonstrate the superiority of our method and the accuracy of LightNet; the pixel-level semantic change detection methods are up to 89% and 86%, respectively.

Using machine learning and data enrichment in the selection of roads for small-scale maps

ABSTRACT Making decisions about which objects to keep or omit is challenging in map design. This process, called selection, constitutes the first operation in cartographic generalization. In this research, a method of automatic road selection for creating small-scale maps using machine learning and data enrichment is proposed. First, the problem of contextual information scarcity concerning roads in the source database is addressed. Additional information concerning the relations between roads and other objects was added (such as centrality and proximity measures). Second, machine learning is used to design automatic selection models based on enriched information. Third, three different road selection approaches are implemented. The baseline approach is following the official map design guidelines. The second approach is based on machine learning using the enriched road database. The third approach is based on an existing structural model. The results of all approaches are compared to existing atlas maps designed by experienced cartographers. The results of the Machine Learning Approaches were most similar to the atlas maps (between 81% and 90% accuracy). The least efficient approaches were the Structural Approach with 32% and the Guidelines Approach with 44% accuracy. We conclude that enriching road data with new contextual information concerning roads and using machine learning is beneficial as the achieved results outperform both Guidelines and Structural Approaches.

Inclined photogrammetry data lightweighting techniques

Since contemporary information-retrieval systems rely heavily on the content of titles and abstracts to identify relevant articles in literature searches, great care should be taken in constructing both. Inclined photogrammetry is an emerging surveying and mapping technology with the advantages of real 3D and multi-view angle, but the huge amount of inclined photogrammetry data makes the application scenarios limited, which leads to the high cost of acquiring inclined photogrammetry data. To address this problem, the lightweighting technology of inclined photogrammetric data is studied. Firstly, the characteristics of inclined photogrammetric data are analysed, the key technology of lightweighting inclined photogrammetric data is studied, and the compression algorithm based on the improved triangular mesh model and the compression algorithm based on the regional chunking model are proposed, which solves the problem of the large volume of inclined photogrammetric data and the inconvenience of using it. The experimental results in small-scale mapping show that the lightweighting of inclined photogrammetric data can be effectively achieved based on the improved triangular mesh model compression algorithm and the regional chunking model compression algorithm, and the optimised combination of the improved triangular mesh model compression algorithm and the regional chunking model compression algorithm can effectively achieve the lightweighting of inclined photogrammetric data.

HAVOC: Small-scale histomic mapping of cancer biodiversity across large tissue distances using deep neural networks.

Intratumoral heterogeneity can wreak havoc on current precision medicine strategies because of challenges in sufficient sampling of geographically separated areas of biodiversity distributed across centimeter-scale tumor distances. To address this gap, we developed a deep learning pipeline that leverages histomorphologic fingerprints of tissue to create "Histomic Atlases of Variation Of Cancers" (HAVOC). Using a number of objective molecular readouts, we demonstrate that HAVOC can define regional cancer boundaries with distinct biology. Using larger tumor specimens, we show that HAVOC can map biodiversity even across multiple tissue sections. By guiding profiling of 19 partitions across six high-grade gliomas, HAVOC revealed that distinct differentiation states can often coexist and be regionally distributed within these tumors. Last, to highlight generalizability, we benchmark HAVOC on additional tumor types. Together, we establish HAVOC as a versatile tool to generate small-scale maps of tissue heterogeneity and guide regional deployment of molecular resources to relevant biodiverse niches.

Enhancing Research Outcomes through Drone-Generated Imagery and Photogrammetry Software Analysis

Drones have gained popularity in numerous fields, including education, where they are employed as valuable tools for enhancing students' knowledge. In particular, the use of drones in land surveying and mapping has revolutionized the industry, replacing manual and time-consuming methods from the 19th century. Unmanned aerial vehicles (UAVs) enable surveyors to cover vast areas easily, even in challenging terrains, while producing high-resolution maps and collecting extensive data efficiently. With the aid of automated software, quality control can be achieved with minimal training. The benefits of drone surveying encompass terrain modeling, surveying, and 3D mapping for GIS purposes, such as topography and volume measurements. The return on investment (ROI) from utilizing drones in mapping and surveying is substantial. Furthermore, UAVs find practical application in close-range mapping, particularly in engineering survey works that traditionally incur significant costs, labor, and time. Low-cost UAVs offer reliable information for various applications, including road design, bridges, and land surveys, matching the accuracy of conventional engineering surveys and policies, particularly for small-scale mapping. UAVs present a stable and rapidly advancing technology, positioning them as competitive alternatives to other surveying methods. This study consists of five phases: preliminary study, data collection, data processing, post-processing, and analysis, with a focus on UAVs as a data processing tool. The project demonstrates the utilization of UAV images and photogrammetry software, which involve capturing overlapping images of the Earth's surface using cameras mounted on drones or airplanes. These images are then processed with photogrammetry software to generate geo-referenced maps, ortho mosaic images, and other valuable outputs. The software is capable of processing both images and lidar points, offering versatility in its applications, including artistic modeling and surveying. The increasing popularity of UAV images and photogrammetry software extends to various fields, such as agriculture, military operations, disaster management, and artistic modeling. As UAVs become more affordable, their accessibility expands to a broader range of users. Aerial mapping with UAVs necessitates mission planning and ground control points, making drones valuable in mapping, search and rescue missions, transportation, and other disaster management applications. Multiple photogrammetry software options are available, each with distinct features and advantages. By leveraging UAV images and photogrammetry software, previously challenging images can be acquired, opening new possibilities for diverse applications.

Influence of contemporary warming on landscape-zonal systems of the East-European sub-continent: Predictive empirical-statistical modeling

Presented in the given article regional geo-ecological prognoses are based on the construction of discrete empirical-statistical models of zonal and regional ecosystems. The analysis was carried out on the examples of the flat territories of the Volga River basin, as well as the northern macro-slope of the Main Caucasian ridge. Regional landscape-ecological calculations and mapping were carried out according to the global climatic models GISS-1988 and E GISS-2007 belong­ing to the family of models of general atmospheric circulation. The strategy of geo-ecological prognosis was as follows: first to identify the selected ecosystem objects (either zonal type of plant formations and regional kinds of landscape) to certain values of contemporary climatic conditions and then to estimate the most probable transformation of the revealed ecological niches of the given objects according to the expected climatic changes for the given prognostic date. The geo-ecological analysis has been performed using mainly two types of empirical models: (a) informational, describing the geo-component interrelations, serving as a basis for the regional bank of their ecological niches that characterizes their parametric space; (b) “fuzzy” set-theoretical models, describing the polysystem units of landscape-zonal organization by operations with the ecological niches as descriptive vectors. Predictions of ecosystem transformations include two stages of analysis: (1) evaluation of the probabilities of changes in the functional states of ecosystems and (2) calculations of the rates of ecosystem transformations. Quantitative predictive analysis is carried out by means of operations with the hydro-thermal niches of zonal-regional ecosystems. The ecological estimates of forthcoming global warming refer first of all to the functional but not structural-morphological prediction. The most probable directions and degree of conversion of the ecosystem are estimated by the maximum values of transformation. The algorithms of predictive calculations are described in detail for both stages of analysis. The results of the zonal-regional prognostic analysis are presented in both graphic-analytical models and small-scale maps.

Data enrichment and supervised learning in road and settlement feature selection for small scale maps

Data enrichment and supervised learning in road and settlement feature selection for small scale maps

Comparison of Areal and Profile Distribution of Magnetic Susceptibility in Steppe Soils of the Russian Plain

A comparative analysis of areal and profile measurements of magnetic susceptibility was carried out in order to improve methods of surface sensing of the earth, as well as to take into account small-scale mapping of soils and the identification of anomalies associated with anthropogenic pollution or violation of the surface layer of soils. Two sites with Haplic Chernozems and one Haplic Kastanozems (Endosalic, Cambic) were studied. Additionally, a catena was studied on the territory of the Ergeninsky upland with the inclusion of sites in various positions of the landscape (eluvial, transeluvial, transeluvial-accumulative). The comparison of the areal and profile magnetic susceptibility measured to a depth of 30 cm showed a direct correlation (R2 = 0.7). It was found that the areal type of survey correctly captures the volumetric magnetic susceptibility (\({{\varkappa }_{{\text{s}}}}\)) to a depth of 30 cm. The variation of \({{\varkappa }_{{\text{s}}}}\) at sites with different types of soils reflects soil-climatic zonality and spatial lithological heterogeneity, expressed in different granulometric and mineralogical composition of the 0–30 cm layer on an area of 10 × 10 m. The areal magnetic susceptibility of soils can be an important additional indicator capable of reflecting the features of soil-forming, lithological and landscape geochemical processes occurring in the upper soil layer. Variation of \({{\varkappa }_{{\text{s}}}}\) at sites in different positions of the landscape occurs under the influence of planar flushing and a change in the direction of iron oxidogenesis processes depending on the position of the soil profile in the relief. The complex of measurements of areal and profile magnetic susceptibility can be used to study soil inhomogeneities caused by anthropogenic, paleocryogenic, geomorphological and lithogenic factors. Such an approach can be widely applied to the study of polluted soils and monitoring of agricultural land.

Agrogenic Soils on the Updated Version of the Soil Map of Russia, 1 : 2.5 M Scale: Classification Diversity and Place in the Soil Cover

Usually, soils changed by farming (agrogenic soils) are not shown on small-scale maps, including the Soil Map of the Russian Federation, 1 : 2.5 M scale (1988). One of the issues of the map updating performed by the Dokuchaev Soil Science Institute is the inclusion of agrogenic soils into the map contents and representation of some of the former native soils as agrogenic soils on the updated map. Preliminarily, all native soils shown on the map have been reclassified into the new Russian soil classification system. Agrogenic soils in this system are separated as agrosoils in different orders and as a specific order of agrozems. Agrogenic soils have been identified in the soil polygons in agreement with the map showing the percentage of arable land in Russia linked to the polygons of the soil map. We have identified the classification position of the initial native soils involved in arable farming. Overall, 114 legend units representing agrosoils and agrozems have been identified. This number is dictated by the diversity of native soils subjected to the agrogenic impact and their agrogenic modifications. Agrogenic soils on the updated map are shown in 4813 polygons out of the total of 25711 map polygons. Chernozems are characterized by the greatest diversity of agrosoils and the largest number of polygons containing various agrochernozems. The order of texture-differentiated soils is also rich in agrogenic soils, both agrosoils and agrozems. Arable soils initially belonging to the order of Al–Fe-humus soils are present in a relatively small number of polygons and are only represented by Al–Fe-humus agrozems. The number of polygons with participation of agrogenic soils and their proportion in the soil cover illustrate geographical patterns of their distribution, in particular, homogenous or mosaic distribution patterns in the areas of different soil orders.

Image-based approximation of derivatives of traditional differential metrics of angular distortion in map projections

ABSTRACT Map projections are imaging procedures used to depict geographic features. We adopt the traditional differential metric and exploit the intrinsic image properties of map projections to establish an image-based differential metric for evaluating distortions in map projections, obtaining an effective, practical, and relatively accurate metric. We use bivariate polynomial functions to approximate the forward and inverse formulae of map projections. Thereafter, the proposed metric is conveniently calculated using the partial derivatives of the approximate forward functions based on polynomial functions, while complicated differential calculations are avoided. Moreover, multiple sampling and image filters mitigate the influence of imaging noise and achieve a high computation precision. Experiments were conducted using the NASA G.Projector mapping software to generate images from more than 200 map projections. Explicit equations of map projections were not required owing to the use of the mapping software. These images were then evaluated using the proposed metric through an implementation in the Julia programming language. The corresponding results confirmed that the proposed metric avoided the drawbacks of the great circle arc metric and provided considerably low errors (1.12° on average) and high consistency (0.999 on average) with respect to the traditional differential metric. Although there were errors, experimental results indicated that feasibility and high usability were achieved by the image-based method for evaluating distortions in small-scale map projections.

Мелкомасштабное ландшафтное картографирование территорий традиционного природопользования Республики Саха (Якутия)

In the Republic of Sakha (Yakutia), there are 63 territories of traditional land use of the Indigenous Minorities of the North within the boundaries of municipal districts and nasleg (lowest municipal division), as well as nomadic tribal communities. Almost 58 % of the republic’s territory is under the traditional land use status. The traditional use of natural resources and traditional lifestyles of indigenous peoples are inextricably linked to the resource potential and ecological state of natural landscapes. The paper is aimed to develop a standardized methodology for the design of a small-scale landscape map of traditional land use in the Republic of Sakha (Yakutia). Based on the review of atlas approaches to landscape structure mapping of protected natural areas, we propose to use a multi-thematic dataset of geospatial layers according to the criteria of the classification of typological, regional and basin categories of landscapes. The dataset includes layers from previously published landscape maps and permafrost-landscape regionalization maps, soil-vegetation maps, and global geospatial data for Hammond relief regions, GMTED2010 digital elevation model and HydroBASINS river basins. Methods for delineation of mapped units include overlay geoprocessing, zonal statistics, and relief analysis. For the basemap, the description of typological landscape units includes landscape subclass-genus-type(subtype) and terrain type. The methodology was tested for the Ust-Maiskij district with predominance of mountain taiga and mid-taiga landscapes and Eveno-Bytantaiskij national district with predominance of mountain-tundra, mountain-woodland and north taiga landscapes. The obtained landscape maps contain 36 typological units that synthesize 6 subclasses, 7 landscape types (subtypes) and 12 terrain types by 5 landscape provinces and large river basins (Lena, Yana, Omoloi and Aldan). Thus, the proposed landscape mapping methodology covers the holistic spatial structure of the leading components, allowing for a multidimensional approach to territorial planning and functional zoning of traditional land use.

Методология геоинформационного мелкомасштабного картографирования геосистем для управления экологическими рисками

Within the framework of the thematic section “Ecological state of the natural environment, natural environmental risks” of the electronic geographical Atlas of North and Northeast Asia, a methodology for small-scale mapping of geosystems has been developed as a procedure for preparing scientific information about a natural geographical object to ensure environmental risk management. The scientific basis of the research is the theory of spatial and temporal organization and the methodology of constructive integration mapping of geosystems. Natural ecological risk is understood as the probability of negative changes in the structure and functioning of geosystems in the case of natural or anthropogenic phenomena and processes in the habitat. The methods of creation, structure, and content of the unified information and cartographic system of the Mongolian-Siberian region of geosystem content of scale 1:5 000 000 have been developed. For these purposes, geographically and conceptually inconsistent maps of the geosystems of the regions of Siberia and Mongolia were analyzed. The patterns of spatial and temporal organization, regional features of functional differentiation of natural systems are revealed. Based on the results of the study, scientific generalizations were made concerning the description of geosystems of regional rank, their typification, classification, and zoning. The prognostic potential of small-scale maps of geosystems in relation to geographical studies of natural environmental risks based on the procedure for analyzing geosystems by typological functional, structural, and dynamic features is revealed. The characteristics of natural factors of the intensity of functioning, ecological functions of geosystems served as indicators in the environmental regulation of the use of natural systems, allowed to correctly substantiate environmental recommendations to minimize undesirable consequences. A specialized classification is demonstrated—a legend and a zoning map of the territory of the Mongolian-Siberian region, reflecting the sequence of multi-stage cartographic studies of natural environmental risk and the structuring of physical and geographical information. The created maps make up the basic set in the structure of spatial data of the electronic Atlas, new maps of geosystems can be created on their basis.

Methodology for surface water flood modelling based on analysis of digital elevation model and hydrological data

A methodology for surface water flood modelling is proposed, based on the use of small-scale mapping tools together with hydrological observation data. To reproduce the flooding surface during extreme floods, information on historical maximum water levels was selected, and a digital elevation model (DEM) was used as the cartographic basis. The proposed methodology is universal and provides possibility to determine the boundaries of the potential flooding area in river sections during extreme water levels, to identify objects in the potential flooding area, as well as to make operational decisions to prevent disastrous situations arising from floods and minimize adverse consequences. The results of application of the proposed method for certain river sections of the North Caucasus, a region characterized by a high degree of flood hazard, are presented.

Soil orders and their areas on the updated soil map of the Russian Federation, 1 : 2.5 M scale

An analysis of the soil cover of Russia as presented on the soil map on a scale of 1 : 2.5 M with the use of a new substantive-genetic soil classification system has been performed at the level of soil orders. The high level of classification-based generalization makes it possible to assess the most general patterns of soil geography and soil resources and to identify changes that have occurred as a result of renaming of each polygon on the map with the use of the new classification. The areas occupied by soil orders have been calculated. In total, there are 24 soil orders on the new map, including 21 orders of natural soils and 3 orders (agrozems, turfzems, stratozems) of anthropogenically transformed soils. Soils of the orders of agro-abrazems, chernozems, and turbozems are not presented on the map. As on most small-scale soil maps of Russia, the zonal regularities of the soil cover in the East European Plain and high lithogenic mosaicity in Central and Eastern Siberia are clearly seen. The new map includes soil orders that were absent on the initial map: cryozems, cryometamorphic and hydrometamorphic soils, lithozems, cryoabrazems, cryoturbozems, urbostratozems, and organo-accumulative soils. Soils characteristic of humid conditions predominate: Al-Fe-humus soils (Podzols) (319.2 M ha, or 19% of the land fund of Russia), gley soils (Gleysols) (223.9 M ha, 13%), texture-differentiated soils (Luvisols and Regosols) (190.8 M ha, 11%), and peat soils (Histosols) (143.5 M ha, 8%) and occupy more than a half of the territory of Russia. The area of humus-accumulative soils most suitable for arable use is 103.6 M ha (6%). Considerable areas are occupied by soils of the orders of cryozems (Turbic Cryosols) (111.4 M ha), iron-metamorphic soils (Chromic Cambisols) (92.7 M ha), structure-metamorphic soils (Cambisols) (47.3 M ha), pale-metamorphic soils (Cambic Cryosols) (12.8 M ha), hydrometamorphic soils (Calcic Gleysols) (4.3 M ha), and cryometamorphic soils (Cambisols Gelic) (3.4 M ha), which corresponds to the vast continental territory of Russia with balanced moisture conditions. Separate place belongs to the soils with strict limitations for use (lithosols (Leptosols), weakly developed soils (Regosols, Nudilithic Leptosols)) but playing important biospheric functions and requiring special protection.

Оценка и картографирование природной пожарной опасности растительности Байкальского региона

The relevance of the work is due to the high natural fire danger of vegetation in the area of the Baikal region (the Irkutsk oblast, the Republic of Buryatia and Zabaykalsky Krai). In this regard, it is important to analyze and identify the local types of plant complexes, assess their natural fire hazard by the characteristic signs of the presence and distribution of plant combustible materials. Based on statistical data for 2000–2020, indicators of fire risk and density, and the area of one burning case were calculated for wood zones. The types of plant complexes are analyzed and identified using the cartographic method. They are evaluated in accordance with the basic principles of forest combustible materials’ fire hazard with the assignment of appropriate classes of natural burning ability to them. The results of the study are reflected on a small-scale map Natural fire danger of vegetation of the Baikal region, which can serve for territory-wide interaction in matters of fire monitoring. It is determined that a significant part of the area’s vegetation has a high and medium natural fire hazard. The highest of that is observed in the southern and central parts of the mentioned lands.