Vegetation Type Map Research Articles

Mapping Vegetation Types and Land Use Dynamics in Kanyabaha Wetland from 1990 to 2021

Wetlands are crucial ecosystems providing essential ecological services, yet they face increasing threats from human activities. This study focuses on Kanyabaha Wetland in Uganda, examining its vegetation dynamics over three decades (1990-2021) using Landsat satellite imagery. The research characterizes land use and cover types including papyrus, grasslands, farmlands, tree plantations, built-up areas, and woodlands. Remote sensing data was processed and classified using ArcMap software, validated through field verification, resulting in high overall accuracy (>75%) across all study years. The images were analyzed using a hybrid of unsupervised (ISO data) and supervised (Maximum Likelihood) classification techniques. Findings reveal significant shifts in vegetation cover, with papyrus dominating initially but declining over time due to expansion in farmlands and settlements. Grasslands also decreased, while areas under farming and built-up structures expanded. Transition matrices illustrate these changes, highlighting stable and shifting landscape dynamics. Statistical analyses indicate a decrease in papyrus cover from 51.5% in 1990 to 39.1% in 2021, while farmland and built-up areas increased from 3.0% to 31.6% and 3.2% to 5.1%, respectively. This study highlights the vulnerability of Kanyabaha Wetland to anthropogenic impacts, necessitating targeted conservation strategies to sustain its ecological integrity amid ongoing land use changes.

U-Net Convolutional Neural Network for Mapping Natural Vegetation and Forest Types from Landsat Imagery in Southeastern Australia.

Accurate and comparable annual mapping is critical to understanding changing vegetation distribution and informing land use planning and management. A U-Net convolutional neural network (CNN) model was used to map natural vegetation and forest types based on annual Landsat geomedian reflectance composite images for a 500 km × 500 km study area in southeastern Australia. The CNN was developed using 2018 imagery. Label data were a ten-class natural vegetation and forest classification (i.e., Acacia, Callitris, Casuarina, Eucalyptus, Grassland, Mangrove, Melaleuca, Plantation, Rainforest and Non-Forest) derived by combining current best-available regional-scale maps of Australian forest types, natural vegetation and land use. The best CNN generated using six Landsat geomedian bands as input produced better results than a pixel-based random forest algorithm, with higher overall accuracy (OA) and weighted mean F1 score for all vegetation classes (93 vs. 87% in both cases) and a higher Kappa score (86 vs. 74%). The trained CNN was used to generate annual vegetation maps for 2000-2019 and evaluated for an independent test area of 100 km × 100 km using statistics describing accuracy regarding the label data and temporal stability. Seventy-six percent of pixels did not change over the 20 years (2000-2019), and year-on-year results were highly correlated (94-97% OA). The accuracy of the CNN model was further verified for the study area using 3456 independent vegetation survey plots where the species of interest had ≥ 50% crown cover. The CNN showed an 81% OA compared with the plot data. The model accuracy was also higher than the label data (76%), which suggests that imperfect training data may not be a major obstacle to CNN-based mapping. Applying the CNN to other regions would help to test the spatial transferability of these techniques and whether they can support the automated production of accurate and comparable annual maps of natural vegetation and forest types required for national reporting.

Aboveground Biomass Inversion Based on Object-Oriented Classification and Pearson–mRMR–Machine Learning Model

Cities play a crucial role in the carbon cycle. Measuring urban aboveground biomass (AGB) is essential for evaluating carbon sequestration. Satellite remote sensing enables large-scale AGB inversion. However, the apparent differences between forest and grassland biomass pose a significant challenge to the accurate estimation of urban AGB using satellite-based data. To address this limitation, this study proposed a novel AGB estimation method using the eastern part of the Zhahe mining area in Huaibei City as the study area, which integrates land cover classification, feature selection, and machine learning modelling to generate high quality biomass maps of different vegetation types in an urban area with complex feature distribution. Utilizing the GEE platform and Sentinel-2 image, we developed an object-oriented machine learning classification algorithm, combining SNIC and GLCM to extract vegetation information. Optimal feature variables for forest and crop-grass AGB inversion were selected using the Pearson–mRMR algorithm. Finally, we constructed nine machine learning models for AGB inversion and selected the model with the highest accuracy to generate the AGB map of the study area. The results of the study are as follows: (1) Compared with the pixel-based classification method, the object-oriented classification method can extract the boundaries of different vegetation types more accurately. (2) Forest AGB is strongly correlated with vegetation indices and physiological parameters, while agri-grass AGB is primarily associated with vegetation indices and vegetation physiological parameters. (3) For forest AGB modelling, the RF-R model outperforms other machine learning models with an R2 of 0.77. For agri-grass AGB modelling, the XGBoost-R model is more accurate, with an R2 of 0.86. (4) The mean forest AGB in the study area was 4.60 kg/m2, while the mean agri-grass AGB was 0.71 kg/m2. High AGB values were predominantly observed in forested areas, which were mainly distributed along roads, waterways, and mountain ranges. Overall, this study contributes to a better understanding of the health of local urban ecosystems and provides valuable insights for ecosystem protection and the sustainable use of natural resources.

Vegetation Type Mapping in Southern Patagonia and Its Relationship with Ecosystem Services, Soil Carbon Stock, and Biodiversity

Vegetation Type (VT) mapping using Optical Earth observation data is essential for the management and conservation of natural resources, as well as for the evaluation of the supply of provisioning ecosystem services (ESs), the maintenance of ecosystem functions, and the conservation of biodiversity in anthropized environments. The main objective of the present work was to determine the spatial patterns of VTs related to climatic, topographic, and spectral variables across Santa Cruz province (Southern Patagonia, Argentina) in order to improve our understanding of land use cover at the regional scale. Also, we examined the spatial relationship between VTs and potential biodiversity (PB), ESs, and soil organic content (SOC) across our study region. We sampled 59,285 sites sorted into 19 major categories of land cover with a reliable discrimination level from field measurements. We selected 31 potential predictive environmental dataset covariates, which represent key factors for the spatial distribution of land cover such as climate (four), topography (three), and spectral (24) factors. All covariate maps were generated or uploaded to the Google Earth Engine cloud-based computing platform for subsequent modeling. A total of 270,292 sampling points were used for validation of the obtained classification map. The main land cover area estimates extracted from the map at the regional level identified about 142,085 km2 of grasslands (representing 58.1% of the total area), 38,355 km2 of Mata Negra Matorral thicket (15.7%), and about 25,189 km2 of bare soil (10.3%). From validation, the Overall Accuracy and the Kappa coefficient values for the classification map were 90.40% and 0.87, respectively. Pure and mixed forests presented the maximum SOC (11.3–11.8 kg m−2), followed by peatlands (10.6 kg m−2) and deciduous Nothofagus forests (10.5 kg m−2). The potential biodiversity was higher in some shrublands (64.1% in Mata Verde shrublands and 63.7% in mixed shrublands) and was comparable to those values found for open deciduous forests (Nothofagus antarctica forest with 60.4%). The provision of ESs presented maximum values at pure evergreen forests (56.7%) and minimum values at some shrubland types (Mata Negra Matorral thicket and mixed shrubland) and steppe grasslands (29.7–30.9%). This study has provided an accurate land cover and VT map that provides crucial information for ecological studies, biodiversity conservation, vegetation management and restoration, and regional strategic decision-making.

Classifying Mountain Vegetation Types Using Object-Oriented Machine Learning Methods Based on Different Feature Combinations

Mountainous vegetation type classification plays a fundamental role in resource investigation in forested areas, making it necessary to accurately identify mountain vegetation types. However, Mountainous vegetation growth is readily affected by terrain and climate, which often makes interpretation difficult. This study utilizes Sentinel-2A images and object-oriented machine learning methods to map vegetation types in the complex mountainous region of Jiuzhaigou County, China, incorporating multiple auxiliary features. The results showed that the inclusion of different features improved the accuracy of mountain vegetation type classification, with terrain features, vegetation indices, and spectral features providing significant benefits. After feature selection, the accuracy of mountain vegetation type classification was further improved. The random forest recursive feature elimination (RF_RFE) algorithm outperformed the RliefF algorithm in recognizing mountain vegetation types. Extreme learning machine (ELM), random forest (RF), rotation forest (ROF), and ROF_ELM algorithms all achieved good classification performance, with an overall accuracy greater than 84.62%. Comparing the mountain vegetation type distribution maps obtained using different classifiers, we found that classification algorithms with the same base classifier ensemble exhibited similar performance. Overall, the ROF algorithm performed the best, achieving an overall accuracy of 89.68%, an average accuracy of 88.48%, and a Kappa coefficient of 0.879.

Inventorisation and Mapping of the Grasslands of the Bassi Wildlife Sanctuary, Rajasthan, India

During the floristic explorations in the Bassi WLS, the vegetation type map is prepared to study the status and composition of grasslands and savannahs of the sanctuary. Further, the grasses and grass associated plant species which are the chief fodder preferences of primary consumers in Bassi Wildlife Sanctuary are documented. A total of 69 taxa under 59 genera belongs to 16 families are identified from the grasslands and savannahs. Disturbance indicators including the invasive alien species in the Bassi WLS which are menace to biodiversity are discussed here.

Evaluating capabilities of machine learning algorithms for aquatic vegetation classification in temperate wetlands using multi-temporal Sentinel-2 data

Different perspectives use of machine learning (ML) algorithms have proven their performance depends on the quality of reference data. This is particularly true when targets are complex environments, such as wetlands, on which a vast majority of studies are site-specific and based on a single date. With this work, an extensive reference dataset of about 400,000 samples was collected, covering nine different sites and multiple seasons, to be considered representative of temperate wetland vegetation communities at continental scale. Starting from this dataset, the performance of selected ML classifiers was compared for detailed wetland vegetation type mapping, using spectral indices (SI) derived from multi-temporal composites of Sentinel-2 as input. Global and per-class accuracy metrics were computed based on four independent training and testing subsets, extracted from the overall dataset, and the impacts of input features variation in number and sites covered were assessed. Our results show a generally higher predictive power for ensemble methods, such as Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), compared to standalone ones, with the notable exception of Support Vector Machine (SVM); the latter in fact, in the algorithm that scored the highest overall accuracy (0.977 ± 0.001) and F-score for all the target classes. Decreasing the number of input features generally resulted in classification accuracy losses, less marked for RF than for SVM, while site-specific algorithms training showed more stability of SVM, thus indicating SVM stronger transferability than RF and XGBoost.

Mapping species assemblages of tropical forests at different hierarchical levels based on multivariate regression trees

BackgroundVegetation distribution maps are of great significance for nature protection and management. In diverse tropical forests, accurate spatial mapping of vegetation types is challenging; the high species diversity and abundance of rare species challenge classification concepts, while remote sensing signals may not vary systematically with species composition, complicating the technical capability for delineating vegetation types in the landscape. MethodsWe used a combination of field-based compositional data and their relations to environmental variables to predict the distribution of forest types in the Wuzhishan National Natural Reserve (WNNR), Hainan Island, China, using multivariate regression trees (MRT). The MRT was based on arboreal vegetation composition in 132 plots of 20 ​m ​× ​20 ​m with a regular spacing of 1 ​km. Apart from the MRT, non-metric multidimensional scaling (NMDS) was used to evaluate vegetation-environment relationships. ResultsThe MRT model worked best when using 14 key environmental variables including topography, climate, latitude and soil, although the difference with the simpler model including only topographical variables was small. The full model classified the 132 plots into 3 vegetation types, 6 formation groups, 20 formations and 65 associations at different hierarchical syntaxonomic levels. This model was the basis for forest vegetation maps for the WNNR. MRT and NMDS showed that elevation was the main driving force for the distribution of vegetation types and formation groups. Climate, latitude, and soil (especially available P), together with topographic variables, all influenced the distribution of formations and associations. ConclusionsWhile elevation determines forest-type distributions, lower-level syntaxonomic forest classes respond to the topographic diversity typical for mountains. Apart from providing the first detailed forest vegetation map for any part of WNNR, we show how, in spite of limitations, MRT with existing environmental data can be a useful method for mapping diverse and remote tropical forests.

Madagascar's extraordinary biodiversity: Evolution, distribution, and use.

Madagascar's biota is hyperdiverse and includes exceptional levels of endemicity. We review the current state of knowledge on Madagascar's past and current terrestrial and freshwater biodiversity by compiling and presenting comprehensive data on species diversity, endemism, and rates of species description and human uses, in addition to presenting an updated and simplified map of vegetation types. We report a substantial increase of records and species new to science in recent years; however, the diversity and evolution of many groups remain practically unknown (e.g., fungi and most invertebrates). Digitization efforts are increasing the resolution of species richness patterns and we highlight the crucial role of field- and collections-based research for advancing biodiversity knowledge and identifying gaps in our understanding, particularly as species richness corresponds closely to collection effort. Phylogenetic diversity patterns mirror that of species richness and endemism in most of the analyzed groups. We highlight humid forests as centers of diversity and endemism because of their role as refugia and centers of recent and rapid radiations. However, the distinct endemism of other areas, such as the grassland-woodland mosaic of the Central Highlands and the spiny forest of the southwest, is also biologically important despite lower species richness. The documented uses of Malagasy biodiversity are manifold, with much potential for the uncovering of new useful traits for food, medicine, and climate mitigation. The data presented here showcase Madagascar as a unique "living laboratory" for our understanding of evolution and the complex interactions between people and nature. The gathering and analysis of biodiversity data must continue and accelerate if we are to fully understand and safeguard this unique subset of Earth's biodiversity.

Integrating plot‐based and remotely sensed data to map vegetation types in a New Zealand warm‐temperate rainforest

AbstractQuestions(1) What can be learned by extending a national classification into unsampled forest types? (2) Are both remotely sensed and environmental predictors needed to model and map associations? (3) For mapping, are LiDAR‐generated canopy structure parameters or reflectance from spectral imagery more useful? (4) How can we assess uncertainty of a final map?LocationWarawara Forest, Northland, New Zealand.MethodsWe sampled 205 vegetation plots and assigned them to an existing national classification using the fuzzy classification framework of noise clustering. Plots too distinct to be assigned were used to define new associations. We produced spatial models of each association using boosted regression trees. Predictors included 11 environmental, 11 canopy reflectance, and 17 canopy structure variables. We created a composite map by assigning each map pixel to the association with the highest occurrence probability. We evaluated uncertainty by examining locations where no class was predicted with probability above 0.2 and by creating a confusion map based on entropy.ResultsForty‐five plots were assigned to six of 79 existing national associations and 147 plots were used to define two new forest associations. Three shrubland types are widespread nationally, whereas two young forest types are northern. Three mature forest types are narrowly distributed nationally, with the new “High‐elevation hardwood forest” largely restricted to Warawara Forest. Three associations were mapped using remotely sensed predictors alone, whereas two also required environmental predictors. Overall, canopy reflectance predictors explained more deviance than canopy structure. Examining locations where no association was predicted well and where multiple associations were predicted equally showed areas mapped as younger forests to have greatest uncertainty.ConclusionsIn answering our questions, we present a vegetation classification and map for Warawara Forest that provides a framework to guide the indigenous people's management responses to threats to valued communities and their species.

An Ultra-Resolution Features Extraction Suite for Community-Level Vegetation Differentiation and Mapping at a Sub-Meter Resolution

This paper presents two categories of features extraction and mapping suite, a very high-resolution suite and an ultra-resolution suite at 2 m and 0.5 m resolutions, respectively, for the differentiation and mapping of land cover and community-level vegetation types. The features extraction flow of the ultra-resolution suite involves pan-sharpening of the multispectral image, color-transformation of the pan-sharpened image, and the generation of panchromatic textural features. The performance of the ultra-resolution features extraction suite was compared with the very high-resolution features extraction suite that involves the calculation of radiometric indices and color-transformation of the multi-spectral image. This research was implemented in three mountainous ecosystems located in a cool temperate region. Three machine learning classifiers, Random Forests, XGBoost, and SoftVoting, were employed with a 10-fold cross-validation method for quantitatively evaluating the performance of the two suites. The ultra-resolution suite provided 5.3% more accuracy than the very high-resolution suite using single-date autumn images. Addition of summer images gained 12.8% accuracy for the ultra-resolution suite and 13.2% accuracy for the very high-resolution suite across all sites, while the ultra-resolution suite showed 4.9% more accuracy than the very high-resolution suite. The features extraction and mapping suites presented in this research are expected to meet the growing need for differentiating land cover and community-level vegetation types at a large scale.

Characterising the Land Surface Phenology of Middle Eastern Countries Using Moderate Resolution Landsat Data

Global change impacts including climate change, increased CO2 and nitrogen deposition can be determined through a more precise characterisation of Land Surface Phenology (LSP) parameters. In addition, accurate estimation of LSP dates is being increasingly used in applications such as mapping vegetation types, yield forecasting, and irrigation management. However, there has not been any attempt to characterise Middle East vegetation phenology at the fine spatial resolution appropriate for such applications. Remote-sensing based approaches have proved to be a useful tool in such regions since access is restricted in some areas due to security issues and their inter-annual vegetation phenology parameters vary considerably because of high uncertainty in rainfall. This study aims to establish for the first time a comprehensive characterisation of the vegetation phenological characteristics of the major vegetation types in the Middle East at a fine spatial resolution of 30 m using Landsat Normalized Difference Vegetation Index (NDVI) time series data over a temporal range of 20 years (2000–2020). Overall, a progressive pattern in phenophases was observed from low to high latitude. The earliest start of the season was concentrated in the central and east of the region associated mainly with grassland and cultivated land, while the significantly delayed end of the season was mainly distributed in northern Turkey and Iran corresponding to the forest, resulting in the prolonged length of the season in the study area. There was a significant positive correlation between LSP parameters and latitude, which indicates a delay in the start of the season of 4.83 days (R2 = 0.86, p < 0.001) and a delay in the end of the season of 6.54 days (R2 = 0.83, p < 0.001) per degree of latitude increase. In addition, we have discussed the advantages of fine resolution LSP parameters over the available coarse datasets and showed how such outputs can improve many applications in the region. This study shows the potential of Landsat data to quantify the LSP of major land cover types in heterogeneous landscapes of the Middle East which enhances our understanding of the spatial-temporal dynamics of vegetation dynamics in arid and semi-arid settings in the world.

A State-of-the-Art Vegetation Map for Jordan: A New Tool for Conservation in a Biodiverse Country

In many countries, including Jordan, the updating of vegetation maps is required to aid in formulating development and management plans for agriculture, forest, and rangeland sectors. Remote sensing data contributes widely to vegetation mapping at different scales by providing multispectral information that can separate and identify different vegetation groups at reasonable accuracy and low cost. Here, we implemented state-of-the-art approaches to develop a vegetation map for Jordan, as an example of how such maps can be produced in regions of high vegetation complexity. Specifically, we used a reciprocal illumination technique that combines extensive ground data (640 vegetation inventory plots) and Sentinel-2 satellite images to produce a categorical vegetation map (scale 1:50,000). Supervised classification was used to translate the spectral characteristics into vegetation types, which were first delimited by the clustering analyses of species composition data from the plots. From the satellite image interpretation, two maps were created: an unsupervised land cover/land use map and a supervised map of present-day vegetation types, both consisting of 18 categories. These new maps should inform ecosystem management and conservation planning decisions in Jordan over the coming years.

Mapping of Urban Vegetation with High-Resolution Remote Sensing: A Review

Green space is increasingly recognized as an important component of the urban environment. Adequate management and planning of urban green space is crucial to maximize its benefits for urban inhabitants and for the urban ecosystem in general. Inventorying urban vegetation is a costly and time-consuming process. The development of new remote sensing techniques to map and monitor vegetation has therefore become an important topic of interest to many scholars. Based on a comprehensive survey of the literature, this review article provides an overview of the main approaches proposed to map urban vegetation from high-resolution remotely sensed data. Studies are reviewed from three perspectives: (a) the vegetation typology, (b) the remote sensing data used and (c) the mapping approach applied. With regard to vegetation typology, a distinction is made between studies focusing on the mapping of functional vegetation types and studies performing mapping of lower-level taxonomic ranks, with the latter mainly focusing on urban trees. A wide variety of high-resolution imagery has been used by researchers for both types of mapping. The fusion of various types of remote sensing data, as well as the inclusion of phenological information through the use of multi-temporal imagery, prove to be the most promising avenues to improve mapping accuracy. With regard to mapping approaches, the use of deep learning is becoming more established, mostly for the mapping of tree species. Through this survey, several research gaps could be identified. Interest in the mapping of non-tree species in urban environments is still limited. The same holds for the mapping of understory species. Most studies focus on the mapping of public green spaces, while interest in the mapping of private green space is less common. The use of imagery with a high spatial and temporal resolution, enabling the retrieval of phenological information for mapping and monitoring vegetation at the species level, still proves to be limited in urban contexts. Hence, mapping approaches specifically tailored towards time-series analysis and the use of new data sources seem to hold great promise for advancing the field. Finally, unsupervised learning techniques and active learning, so far rarely applied in urban vegetation mapping, are also areas where significant progress can be expected.

Very High-Resolution Imagery and Machine Learning for Detailed Mapping of Riparian Vegetation and Substrate Types

Riparian zones fulfill diverse ecological and economic functions. Sustainable management requires detailed spatial information about vegetation and hydromorphological properties. In this study, we propose a machine learning classification workflow to map classes of the thematic levels Basic surface types (BA), Vegetation units (VE), Dominant stands (DO) and Substrate types (SU) based on multispectral imagery from an unmanned aerial system (UAS). A case study was carried out in Emmericher Ward on the river Rhine, Germany. The results showed that: (I) In terms of overall accuracy, classification results decreased with increasing detail of classes from BA (88.9%) and VE (88.4%) to DO (74.8%) or SU (62%), respectively. (II) The use of Support Vector Machines and Extreme Gradient Boost algorithms did not increase classification performance in comparison to Random Forest. (III) Based on probability maps, classification performance was lower in areas of shaded vegetation and in the transition zones. (IV) In order to cover larger areas, a gyrocopter can be used applying the same workflow and achieving comparable results as by UAS for thematic levels BA, VE and homogeneous classes covering larger areas. The generated classification maps are a valuable tool for ecologically integrated water management.

Considering vegetation flood tolerance in estuary opening decisions

Some estuaries close intermittently when sand is deposited at their mouths and there is insufficient hydraulic energy to breach it. When closed, water levels may rise and flood surrounding land. These floods may adversely impact infrastructure, agriculture and ecosystems that are intolerant of inundation. Consequently, there is often pressure for managers to mechanically open such estuaries. Artificial openings can also cause serious adverse impacts, including mass fish kills, and there may be counter-pressure to leave the estuary closed. Thus, artificial estuary opening is complex and often contested. In response, managers are increasingly using quantitative measures of expected impact to inform and justify their decisions. Here, we demonstrate, using a case study, a tractable approach that quantifies the expected adverse impacts on native estuarine vegetation resulting from inundation. We used structured expert (n = 4) elicitation to gather mortality estimates of 18 prominent estuarine plant taxa under different inundation scenarios (3 salinities, 5 durations). We then used these data to quantify the expected impact on discrete vegetation types, each of which is characterised by one or more of the selected species. Using 1 cm LiDAR-derived elevation data and pre-existing mapping of vegetation types for specific estuaries, we simulated 105 inundation scenarios (7 depths; 3 salinities; 5 durations). From the extent of different vegetation types inundated in the simulations, and the various expected impacts of inundation on each vegetation type, we computed estuary-wide impact scores. These impact scores express the degree of vegetation mortality expected under a given flood scenario for a given estuary. We demonstrated this approach by computing impact scores for 28 artificially opened estuaries in Victoria, Australia. These scores can be used alongside other data (for infrastructure, other biota, etc), to inform mouth-opening decisions. The approach described could be applied to any estuary, provided there is adequate vegetation mapping, elevation data and knowledge or data on the impacts of flooding on the vegetation.

Mapping South America’s Drylands through Remote Sensing—A Review of the Methodological Trends and Current Challenges

The scientific grasp of the distribution and dynamics of land use and land cover (LULC) changes in South America is still limited. This is especially true for the continent’s hyperarid, arid, semiarid, and dry subhumid zones, collectively known as drylands, which are under-represented ecosystems that are highly threatened by climate change and human activity. Maps of LULC in drylands are, thus, essential in order to investigate their vulnerability to both natural and anthropogenic impacts. This paper comprehensively reviewed existing mapping initiatives of South America’s drylands to discuss the main knowledge gaps, as well as central methodological trends and challenges, for advancing our understanding of LULC dynamics in these fragile ecosystems. Our review centered on five essential aspects of remote-sensing-based LULC mapping: scale, datasets, classification techniques, number of classes (legends), and validation protocols. The results indicated that the Landsat sensor dataset was the most frequently used, followed by AVHRR and MODIS, and no studies used recently available high-resolution satellite sensors. Machine learning algorithms emerged as a broadly employed methodology for land cover classification in South America. Still, such advancement in classification methods did not yet reflect in the upsurge of detailed mapping of dryland vegetation types and functional groups. Among the 23 mapping initiatives, the number of LULC classes in their respective legends varied from 6 to 39, with 1 to 14 classes representing drylands. Validation protocols included fieldwork and automatic processes with sampling strategies ranging from solely random to stratified approaches. Finally, we discussed the opportunities and challenges for advancing research on desertification, climate change, fire mapping, and the resilience of dryland populations. By and large, multi-level studies for dryland vegetation mapping are still lacking.

Mapping native and non-native vegetation in the Brazilian Cerrado using freely available satellite products

Native vegetation across the Brazilian Cerrado is highly heterogeneous and biodiverse and provides important ecosystem services, including carbon and water balance regulation, however, land-use changes have been extensive. Conservation and restoration of native vegetation is essential and could be facilitated by detailed landcover maps. Here, across a large case study region in Goiás State, Brazil (1.1 Mha), we produced physiognomy level maps of native vegetation (n = 8) and other landcover types (n = 5). Seven different classification schemes using different combinations of input satellite imagery were used, with a Random Forest classifier and 2-stage approach implemented within Google Earth Engine. Overall classification accuracies ranged from 88.6–92.6% for native and non-native vegetation at the formation level (stage-1), and 70.7–77.9% for native vegetation at the physiognomy level (stage-2), across the seven different classifications schemes. The differences in classification accuracy resulting from varying the input imagery combination and quality control procedures used were small. However, a combination of seasonal Sentinel-1 (C-band synthetic aperture radar) and Sentinel-2 (surface reflectance) imagery resulted in the most accurate classification at a spatial resolution of 20 m. Classification accuracies when using Landsat-8 imagery were marginally lower, but still reasonable. Quality control procedures that account for vegetation burning when selecting vegetation reference data may also improve classification accuracy for some native vegetation types. Detailed landcover maps, produced using freely available satellite imagery and upscalable techniques, will be important tools for understanding vegetation functioning at the landscape scale and for implementing restoration projects.

A comparison of three ways to assemble wall-to-wall maps from distribution models of vegetation types

ABSTRACT Distribution modeling methods are used to provide occurrence probability surfaces for modeled targets. While most often used for modeling species, distribution modeling methods can also be applied to vegetation types. However, surfaces provided by distribution modeling need to be transformed into classified wall-to-wall maps of vegetation types to be useful for practical purposes, such as nature management and environmental planning. The paper compares the performance of three methods for assembling predictions for multiple vegetation types, modeled individually, into a wall-to-wall map. The authors used grid-cell based probability surfaces from distribution models of 31 vegetation types to test the three assembly methods. The first, a probability-based method, selected for each grid cell the vegetation type with the highest predicted probability of occurrence in that cell. The second, a performance-based method, assigned the vegetation types, ordered from high to low model performance, to a fraction of the grid cells given by the vegetation type’s prevalence in the study area. The third, a prevalence-based method, differed from the performance-based method by assigning vegetation types in the order from low to high prevalence. Thus the assembly methods worked in two principally different ways: the probability-based method assigned vegetation types to grid cells in a cell-by-cell manner, and both the performance-based method and prevalence-based method assigned them in a type-by-type manner. All methods were evaluated by use of reference data collected in the field, more or less independently of the data used to parameterize the vegetation-type models. Quantity, allocation, and total disagreement, as well as proportional dissimilarity metrics, were used for evaluation of assembly methods. Overlay analysis showed 38.1% agreement between all three assembly methods. The probability-based method had the lowest total disagreement with, and proportional dissimilarity from, the reference datasets, but the differences between the three methods were small. The three assembly methods differed strongly with respect to the distribution of the total disagreement on its quantity and allocation components: the cell-by-cell assignment method strongly favored allocation disagreement and the type-by-type methods strongly favored quantity disagreement. The probability-based method best reproduced the general pattern of variation across the study area, but at the cost of many rare vegetation types, which were left out of the assembled map. By contrast, the prevalence-based and performance-based methods represented vegetation types in accordance with nationwide area statistics. The results show that maps of vegetation types with wall-to-wall coverage can be assembled from individual distribution models with a quality acceptable for indicative purposes, but all the three tested methods currently also have shortcomings. The results also indicate specific points in the methodology for map assembly that may be improved.

Reestablishing natural fire regimes to restore forest structure in California’s red fir forests: The importance of regional context

The reestablishment of natural fire regimes can have numerous benefits for forest ecosystems, including the restoration of stand structure through a reduction in tree densities and increased representation of large diameter trees. However, fire effects may depend on how departed the ecosystem is from its historical fire frequency. Red fir (Abies magnifica) forests occupy a broad geographic area across which historical fire return intervals and stand structures vary. Using historical stand inventory data from the Vegetation Type Mapping (VTM) project, we evaluated red fir forests in the Sierra Nevada in California and the Cascade-Klamath region of northwestern California and southern Oregon to determine how reintroduced fire effects vary regionally and if these differences are related to historical fire return intervals or structural conditions. We sampled a total of 29 overlapping fires and found that reestablishing fire in red fir forests consistently restored historical forest structure across a wide geographic range by reducing the density of small trees and maintaining large trees. However, the effect of fire was most evident in the Sierra Nevada where the percent difference in total tree density between unburned and burned plots was significantly greater (77% difference) than in the Cascade-Klamath (53% difference), and burned plots in the Sierra Nevada had significantly lower densities of both small (<30 cm dbh) and medium sized trees (30–60 cm dbh). These stronger fire effects may be related to greater departure from reference fire return intervals in the Sierra Nevada, as well as the region’s warmer and drier conditions increasing the availability of fuel to burn and susceptibility of trees to fire-related mortality. We found that departure from reference fire return intervals followed a similar pattern to departure from historical tree density in both study regions. Unburned plots were 61% departed from reference fire return intervals in the Cascade-Klamath and 69% departed in the Sierra Nevada. In these same plots, departure from VTM total tree density estimates were 37% in the Cascade-Klamath and 44% in the Sierra Nevada. We suggest that incorporating historical references for structural conditions together with regional or local estimates of historical fire return intervals contributes to an improved understanding of how reference conditions varied at local and regional scales, and their importance in the restoration of fire-dependent forests.