Habitat Mapping and Quality Assessment of NATURA 2000 Heathland Using Airborne Imaging Spectroscopy

The utility of airborne hyperspectral and satellite multispectral images in identifying Natura 2000 non-forest habitats for conservation purposes

Aerial hyperspectral and multispectral satellite data are the two most commonly used datasets to identify natural and semi-natural vegetation. However, there is no documented analysis based on data from several areas concerning the difference in the classification accuracy of non-forest Natura 2000 habitat with the use of aerial hyperspectral and satellite multispectral data. Also, there is no recommendation, on which habitat can be classified with sufficient accuracy using free multispectral images. This study aimed to analyse the difference in classification accuracy of Natura 2000 habitats representing: meadows, grasslands, heaths and mires between data with different spectral resolutions and the results utility for nature conservation compared to conventional maps. The analysis was conducted in five study areas in Poland. The classification was performed on multispectral Sentinel-2 (S2) and hyperspectral HySpex (HS) images using the Random Forest algorithm. Based on the results, it can be stated that the use of HS data resulted in higher classification accuracy, on average 0.14, than using S2 images, regardless of the area of the habitat. However, the difference in accuracy was not constant, varying by area and habitat characterisation. Greater differences in accuracy were observed for areas where habitats were characterised by high α-diversity or β-diversity. The HS and S2 data make it possible to create maps that provide a great deal of new knowledge about the distribution of Natura 2000 habitats, which is necessary for the management of protected areas. The obtained results indicate that by using S2 images it is possible to identify, at a satisfactory level, alluvial meadows and grassland. For heaths and mires, using HS data improved the results, but it is also possible to acquire general distribution of these classes, whereas HS images are obligatory for mapping salt, Molinia and lowland hay meadows.

Parcel-Level Mapping of Horticultural Crop Orchards in Complex Mountain Areas Using VHR and Time-Series Images

Accurate and reliable farmland crop mapping is an important foundation for relevant departments to carry out agricultural management, crop planting structure adjustment and ecological assessment. The current crop identification work mainly focuses on conventional crops, and there are few studies on parcel-level mapping of horticultural crops in complex mountainous areas. Using Miaohou Town, China, as the research area, we developed a parcel-level method for the precise mapping of horticultural crops in complex mountainous areas using very-high-resolution (VHR) optical images and Sentinel-2 optical time-series images. First, based on the VHR images with a spatial resolution of 0.55 m, the complex mountainous areas were divided into subregions with their own independent characteristics according to a zoning and hierarchical strategy. The parcels in the different study areas were then divided into plain, greenhouse, slope and terrace parcels according to their corresponding parcel characteristics. The edge-based model RCF and texture-based model DABNet were subsequently used to extract the parcels according to the characteristics of different regions. Then, Sentinel-2 images were used to construct the time-series characteristics of different crops, and an LSTM algorithm was used to classify crop types. We then designed a parcel filling strategy to determine the categories of parcels based on the classification results of the time-series data, and accurate parcel-level mapping of a horticultural crop orchard in a complex mountainous area was finally achieved. Based on visual inspection, this method appears to effectively extract farmland parcels from VHR images of complex mountainous areas. The classification accuracy reached 93.01%, and the Kappa coefficient was 0.9015. This method thus serves as a methodological reference for parcel-level horticultural crop mapping and can be applied to the development of local precision agriculture.

Functional Analysis for Habitat Mapping in a Special Area of Conservation Using Sentinel-2 Time-Series Data

The mapping and monitoring of natural and semi-natural habitats are crucial activities and are regulated by European policies and regulations, such as the 92/43/EEC. In the Mediterranean area, which is characterized by high vegetational and environmental diversity, the mapping and monitoring of habitats are particularly difficult and often exclusively based on in situ observations. In this scenario, it is necessary to automate the generation of updated maps to support the decisions of policy makers. At present, the availability of high spatiotemporal resolution data provides new possibilities for improving the mapping and monitoring of habitats. In this work, we present a methodology that, starting from remotely sensed time-series data, generates habitat maps using supervised classification supported by Functional Data Analysis. We constructed the methodology using Sentinel-2 data in the Mediterranean Special Area of Conservation “Gola di Frasassi” (Code: IT5320003). In particular, the training set uses 308 field plots with 11 target classes (five forests, two shrubs, one grassland, one mosaic, one extensive crop, and one urban land). Starting from vegetation index time-series data, Functional Principal Component Analysis was applied to derive FPCA scores and components. In particular, in the classification stage, the FPCA scores are considered as features. The obtained results out-performed a previous map derived from photo-interpretation by domain experts. We obtained an overall accuracy of 85.58% using vegetation index time-series, topography, and lithology data. The main advantages of the proposed approach are the capability to efficiently compress high dimensional data (dense remote-sensing time series) providing results in a compact way (e.g., FPCA scores and mean seasonal time profiles) that: (i) facilitate the link between remote sensing with habitat mapping and monitoring and their ecological interpretation and (ii) could be complementary to species-based approaches in plant community ecology and phytosociology.

Can a Hierarchical Classification of Sentinel-2 Data Improve Land Cover Mapping?

Monitoring of land cover plays an important role in effective environmental management, assessment of natural resources, environmental protection, urban planning and sustainable development. Increasing demand for accurate and repeatable information on land cover and land cover changes causes rapid development of the advanced, machine learning algorithms dedicated to land cover mapping using satellite images. Free and open access to Sentinel-2 data, characterized with high spatial and temporal resolution, increased the potential to map and to monitor land surface with high accuracy and frequency. Despite a considerable number of approaches towards land cover classification based on satellite data, there is still a challenge to clearly separate complex land cover classes, for example grasslands, arable land and wetlands. The aim of this study is to examine, whether a hierarchal classification of Sentinel-2 data can improve the accuracy of land cover mapping and delineation of complex land cover classes. The study is conducted in the Lodz Province, in central Poland. The pixel-based land cover classification is carried out using the machine learning Random Forest (RF) algorithm, based on a time series of Sentinel-2 imagery acquired in 2020. The following nine land cover classes are mapped: sealed surfaces, woodland broadleaved, woodland coniferous, shrubs, permanent herbaceous (grassy cover), periodically herbaceous (i.e., arable land), mosses, non-vegetated (bare soil) and water bodies. The land cover classification is conducted following two approaches: (1) flat, where all land cover classes are classified together, and (2) hierarchical, where the stratification is applied to first separate the most stable land cover classes and then classifying the most problematic once. The national databases served as the source of the reference sampling plots for the classification process. The process of selection and verification of the reference sampling plots is performed automatically. To assess the stability of the classification models the classification processes are performed iteratively. The results of this study confirmed that the hierarchical approach gave more accurate results compared to the commonly used flat approach. The median of the overall accuracy (OA) of the hierarchical classification was higher by 3–9 percentage points compared to the flat one. Of interest, the OA of the hierarchical classification reached 0.93–0.99, whereas the flat approach reached 0.90. Individual classes are also better classified in the hierarchical approach.

A Machine Learning Framework for the Classification of Natura 2000 Habitat Types at Large Spatial Scales Using MODIS Surface Reflectance Data

Anthropogenic climate and land use change is causing rapid shifts in the distribution and composition of habitats with profound impacts on ecosystem biodiversity. The sustainable management of ecosystems requires monitoring programmes capable of detecting shifts in habitat distribution and composition at large spatial scales. Remote sensing observations facilitate such efforts as they enable cost-efficient modelling approaches that utilize publicly available datasets and can assess the status of habitats over extended periods of time. In this study, we introduce a modelling framework for habitat monitoring in Germany using readily available MODIS surface reflectance data. We developed supervised classification models that allocate (semi-)natural areas to one of 18 classes based on their similarity to Natura 2000 habitat types. Three machine learning classifiers, i.e., Support Vector Machines (SVM), Random Forests (RF), and C5.0, and an ensemble approach were employed to predict habitat type using spectral signatures from MODIS in the visible-to-near-infrared and short-wave infrared. The models were trained on homogenous Special Areas of Conservation that are predominantly covered by a single habitat type with reference data from 2013, 2014, and 2016 and tested against ground truth data from 2010 and 2019 for independent model validation. Individually, the SVM and RF methods achieved better overall classification accuracies (SVM: 0.72–0.93%, RF: 0.72–0.94%) than the C5.0 algorithm (0.66–0.93%), while the ensemble classifier developed from the individual models gave the best performance with overall accuracies of 94.23% for 2010 and 80.34% for 2019 and also allowed a robust detection of non-classifiable pixels. We detected strong variability in the cover of individual habitat types, which were reduced when aggregated based on their similarity. Our methodology is capable to provide quantitative information on the spatial distribution of habitats, differentiate between disturbance events and gradual shifts in ecosystem composition, and could successfully allocate natural areas to Natura 2000 habitat types.

Toward a High Spatial Resolution Aerial Monitoring Network for Nature Conservation—How Can Remote Sensing Help Protect Natural Areas?

Aerial surveys have always significantly contributed to the accurate mapping of certain geographical phenomena. Remote sensing opened up new perspectives in nature monitoring with state-of-the-art technical solutions using modern onboard recording equipment. We developed the technical background and the methodology that supports detailed and cost-effective monitoring of a network of natural areas, thereby detecting temporal changes in the spatial pattern of land cover, species, biodiversity, and other natural features. In this article, we share our experiences of the technical background, geometric accuracy and results of comparisons with selected Copernicus Land Monitoring products and an Ecosystem Map based on the testing of our methodology at 25 sites in Hungary. We combined a high-spatial-resolution aerial remote sensing service with field studies to support an efficient nature conservation monitoring network at 25 permanent sites. By analyzing annually (or more frequently) orthophotos taken with a range of 0.5–5 cm spatial resolution and 3D surface models of aerial surveys, it is possible to map the upper canopy of vegetation species. Furthermore, it allows us to accurately follow the changes in the dynamics at the forest edge and upper canopy, or the changes in species’ dominance in meadows. Additionally, spatial data obtained from aerial surveys and field studies can expand the knowledge base of the High-Resolution Aerial Monitoring Network (HRAMN) and support conservation and restoration management. A well-conducted high-resolution survey can reveal the impacts of land interventions and habitat regeneration. By building the HRAMN network, nature conservation could have an up-to-date database that could prompt legal processes, establish protection designation procedures and make environmental habitat management more cost-effective. Landscape protection could also utilize the services of HRAMN in planning and risk reduction interventions through more reliable inputs to environmental models.

Using UAV Imagery to Detect and Map Woody Species Encroachment in a Subalpine Grassland: Advantages and Limits

Woody species encroachment on grassland ecosystems is occurring worldwide with both negative and positive consequences for biodiversity conservation and ecosystem services. Remote sensing and image analysis represent useful tools for the monitoring of this process. In this paper, we aimed at evaluating quantitatively the potential of using high-resolution UAV imagery to monitor the encroachment process during its early development and at comparing the performance of manual and semi-automatic classification methods. The RGB images of an abandoned subalpine grassland on the Western Italian Alps were acquired by drone and then classified through manual photo-interpretation, with both pixel- and object-based semi-automatic models, using machine-learning algorithms. The classification techniques were applied at different resolution levels and tested for their accuracy against reference data including measurements of tree dimensions collected in the field. Results showed that the most accurate method was the photo-interpretation (≈99%), followed by the pixel-based approach (≈86%) that was faster than the manual technique and more accurate than the object-based one (≈78%). The dimensional threshold for juvenile tree detection was lower for the photo-interpretation but comparable to the pixel-based one. Therefore, for the encroachment mapping at its early stages, the pixel-based approach proved to be a promising and pragmatic choice.

Farmland Parcel Mapping in Mountain Areas Using Time-Series SAR Data and VHR Optical Images

Accurate, timely, and reliable farmland mapping is a prerequisite for agricultural management and environmental assessment in mountainous areas. However, in these areas, high spatial heterogeneity and diversified planting structures together generate various small farmland parcels with irregular shapes that are difficult to accurately delineate. In addition, the absence of optical data caused by the cloudy and rainy climate impedes the use of time-series optical data to distinguish farmland from other land use types. Automatic delineation of farmland parcels in mountain areas is still a very difficult task. This paper proposes an innovative precise farmland parcel extraction approach supported by very high resolution(VHR) optical image and time series synthetic aperture radar(SAR) data. Firstly, Google satellite imagery with a spatial resolution of 0.55 m was used for delineating the boundaries of ground parcel objects in mountainous areas by a hierarchical extraction scheme. This scheme divides farmland into four types based on the morphological features presented in optical imagery, and designs different extraction models to produce each farmland type, respectively. The potential farmland parcel distribution map is then obtained by the layered recombination of these four farmland types. Subsequently, the time profile of each parcel in this map was constructed by five radar variables from the Sentinel-1A dataset, and the time-series classification method was used to distinguish farmland parcels from other types. An experiment was carried out in the north of Guiyang City, Guizhou Province, Southwest China. The result shows that, the producer’s accuracy of farmland parcels obtained by the hierarchical scheme is increased by 7.39% to 96.38% compared with that without this scheme, and the time-series classification method produces an accuracy of 80.83% to further obtain the final overall accuracy of 96.05% for the farmland parcel maps, showing a good performance. In addition, through visual inspection, this method has a better suppression effect on background noise in mountainous areas, and the extracted farmland parcels are closer to the actual distribution of the ground farmland.

National Scale Land Cover Classification for Ecosystem Services Mapping and Assessment, Using Multitemporal Copernicus EO Data and Google Earth Engine

Land-Use/Land-Cover (LULC) products are a common source of information and a key input for spatially explicit models of ecosystem service (ES) supply and demand. Global, continental, and regional, readily available, and free land-cover products generated through Earth Observation (EO) data, can be potentially used as relevant to ES mapping and assessment processes from regional to national scales. However, several limitations exist in these products, highlighting the need for timely land-cover extraction on demand, that could replace or complement existing products. This study focuses on the development of a classification workflow for fine-scale, object-based land cover mapping, employed on terrestrial ES mapping, within the Greek terrestrial territory. The processing was implemented in the Google Earth Engine cloud computing environment using 10 m spatial resolution Sentinel-1 and Sentinel-2 data. Furthermore, the relevance of different training data extraction strategies and temporal EO information for increasing the classification accuracy was also evaluated. The different classification schemes demonstrated differences in overall accuracy ranging from 0.88% to 4.94% with the most accurate classification scheme being the manual sampling/monthly feature classification achieving a 79.55% overall accuracy. The classification results suggest that existing LULC data must be cautiously considered for automated extraction of training samples, in the case of new supervised land cover classifications aiming also to discern complex vegetation classes. The code used in this study is available on GitHub and runs on the Google Earth Engine web platform.

Combining Multiband Remote Sensing and Hierarchical Distance Sampling to Establish Drivers of Bird Abundance

Information on habitat preferences is critical for the successful conservation of endangered species. For many species, especially those living in remote areas, we currently lack this information. Time and financial resources to analyze habitat use are limited. We aimed to develop a method to describe habitat preferences based on a combination of bird surveys with remotely sensed fine-scale land cover maps. We created a blended multiband remote sensing product from SPOT 6 and Landsat 8 data with a high spatial resolution. We surveyed populations of three bird species (Yellow-breasted Bunting Emberiza aureola, Ochre-rumped Bunting Emberiza yessoensis, and Black-faced Bunting Emberiza spodocephala) at a study site in the Russian Far East using hierarchical distance sampling, a survey method that allows to correct for varying detection probability. Combining the bird survey data and land cover variables from the remote sensing product allowed us to model population density as a function of environmental variables. We found that even small-scale land cover characteristics were predictable using remote sensing data with sufficient accuracy. The overall classification accuracy with pansharpened SPOT 6 data alone amounted to 71.3%. Higher accuracies were reached via the additional integration of SWIR bands (overall accuracy = 73.21%), especially for complex small-scale land cover types such as shrubby areas. This helped to reach a high accuracy in the habitat models. Abundances of the three studied bird species were closely linked to the proportion of wetland, willow shrubs, and habitat heterogeneity. Habitat requirements and population sizes of species of interest are valuable information for stakeholders and decision-makers to maximize the potential success of habitat management measures.

Mapping Succession in Non-Forest Habitats by Means of Remote Sensing: Is the Data Acquisition Time Critical for Species Discrimination?

The process of secondary succession is one of the most significant threats to non-forest (natural and semi-natural open) Natura 2000 habitats in Poland; shrub and tree encroachment taking place on abandoned, low productive agricultural areas, historically used as pastures or meadows, leads to changes to the composition of species and biodiversity loss, and results in landscape transformations. There is a perceived need to create a methodology for the monitoring of vegetation succession by airborne remote sensing, both from quantitative (area, volume) and qualitative (plant species) perspectives. This is likely to become a very important issue for the effective protection of natural and semi-natural habitats and to advance conservation planning. A key variable to be established when implementing a qualitative approach is the remote sensing data acquisition date, which determines the developmental stage of trees and shrubs forming the succession process. It is essential to choose the optimal date on which the spectral and geometrical characteristics of the species are as different from each other as possible. As part of the research presented here, we compare classifications based on remote sensing data acquired during three different parts of the growing season (spring, summer and autumn) for five study areas. The remote sensing data used include high-resolution hyperspectral imagery and LiDAR (Light Detection and Ranging) data acquired simultaneously from a common aerial platform. Classifications are done using the random forest algorithm, and the set of features to be classified is determined by a recursive feature elimination procedure. The results show that the time of remote sensing data acquisition influences the possibility of differentiating succession species. This was demonstrated by significant differences in the spatial extent of species, which ranged from 33.2% to 56.2% when comparing pairs of maps, and differences in classification accuracies, which when expressed in values of Cohen’s Kappa reached ~0.2. For most of the analysed species, the spring and autumn dates turned out to be slightly more favourable than the summer one. However, the final recommendation for the data acquisition time should take into consideration the phenological cycle of deciduous species present within the research area and the abiotic conditions.

Multitemporal Hyperspectral Data Fusion with Topographic Indices—Improving Classification of Natura 2000 Grassland Habitats

Accurately identifying Natura 2000 habitat areas with the support of remote sensing techniques is becoming increasingly feasible. Various data types and methods are used for this purpose, and the fusion of data from various sensors and temporal periods (terms) within the phenological cycle allows natural habitats to be precisely identified. This research was aimed at selecting optimal datasets to classify three grassland Natura 2000 habitats (codes 6210, 6410 and 6510) in the Ostoja Nidziańska Natura 2000 site in Poland based on hyperspectral imagery and botanical on-ground reference data acquired in three terms during one vegetative period in 2017 (May, July and September), as well as a digital terrain model (DTM) obtained by airborne laser scanning (ALS). The classifications were carried out using a random forest (RF) algorithm on minimum noise fraction (MNF) transform output bands obtained for single terms, as well as data fusion combining the topographic indices (TOPO) calculated from the DTM, multitemporal hyperspectral data, or a combination of the two. The classification accuracy statistics were analysed in various combinations based on the datasets and their terms of acquisition. Topographic indices improved the classification accuracy of habitats 6210 and 6410, with the greatest impact noted in increased classification accuracy of xerothermic grasslands. The best terms for identifying specific habitats were autumn for 6510 and summer for 6210 and 6410, while the best results overall were obtained by combining data from all terms. The highest obtained values of the F1 coefficient were 84.5% for habitat 6210, 83.2% for habitat 6410, and 69.9% for habitat 6510. Comparing the data fusion results for habitats 6210 and 6410, greater accuracy was obtained by adding topographic indices to multitemporal hyperspectral data, while for habitat 6510, greater accuracy was obtained by fusing only multitemporal hyperspectral data.

Object-Based Land Cover Classification of Cork Oak Woodlands using UAV Imagery and Orfeo ToolBox

This paper investigates the reliability of free and open-source algorithms used in the geographical object-based image classification (GEOBIA) of very high resolution (VHR) imagery surveyed by unmanned aerial vehicles (UAVs). UAV surveys were carried out in a cork oak woodland located in central Portugal at two different periods of the year (spring and summer). Segmentation and classification algorithms were implemented in the Orfeo ToolBox (OTB) configured in the QGIS environment for the GEOBIA process. Image segmentation was carried out using the Large-Scale Mean-Shift (LSMS) algorithm, while classification was performed by the means of two supervised classifiers, random forest (RF) and support vector machines (SVM), both of which are based on a machine learning approach. The original, informative content of the surveyed imagery, consisting of three radiometric bands (red, green, and NIR), was combined to obtain the normalized difference vegetation index (NDVI) and the digital surface model (DSM). The adopted methodology resulted in a classification with higher accuracy that is suitable for a structurally complex Mediterranean forest ecosystem such as cork oak woodlands, which are characterized by the presence of shrubs and herbs in the understory as well as tree shadows. To improve segmentation, which significantly affects the subsequent classification phase, several tests were performed using different values of the range radius and minimum region size parameters. Moreover, the consistent selection of training polygons proved to be critical to improving the results of both the RF and SVM classifiers. For both spring and summer imagery, the validation of the obtained results shows a very high accuracy level for both the SVM and RF classifiers, with kappa coefficient values ranging from 0.928 to 0.973 for RF and from 0.847 to 0.935 for SVM. Furthermore, the land cover class with the highest accuracy for both classifiers and for both flights was cork oak, which occupies the largest part of the study area. This study shows the reliability of fixed-wing UAV imagery for forest monitoring. The study also evidences the importance of planning UAV flights at solar noon to significantly reduce the shadows of trees in the obtained imagery, which is critical for classifying open forest ecosystems such as cork oak woodlands.

Multiple Flights or Single Flight Instrument Fusion of Hyperspectral and ALS Data? A Comparison of their Performance for Vegetation Mapping

Fusion of remote sensing data often improves vegetation mapping, compared to using data from only a single source. The effectiveness of this fusion is subject to many factors, including the type of data, collection method, and purpose of the analysis. In this study, we compare the usefulness of hyperspectral (HS) and Airborne Laser System (ALS) data fusion acquired in separate flights, Multiple Flights Data Fusion (MFDF), and during a single flight through Instrument Fusion (IF) for the classification of non-forest vegetation. An area of 6.75 km2 was selected, where hyperspectral and ALS data was collected during two flights in 2015 and one flight in 2017. This data was used to classify three non-forest Natura 2000 habitats i.e., Xeric sand calcareous grasslands (code 6120), alluvial meadows of river valleys of the Cnidion dubii (code 6440), species-rich Nardus grasslands (code 6230) using a Random Forest classifier. Our findings show that it is not possible to determine which sensor, HS, or ALS used independently leads to a higher classification accuracy for investigated Natura 2000 habitats. Concurrently, increased stability and consistency of classification results was confirmed, regardless of the type of fusion used; IF, MFDF and varied information relevance of single sensor data. The research shows that the manner of data collection, using MFDF or IF, does not determine the level of relevance of ALS or HS data. The analysis of fusion effectiveness, gauged as the accuracy of the classification result and time consumed for data collection, has shown a superiority of IF over MFDF. IF delivered classification results that are more accurate compared to MFDF. IF is always cheaper than MFDF and the difference in effectiveness of both methods becomes more pronounced when the area of aerial data collection becomes larger.

Classification of Expansive Grassland Species in Different Growth Stages Based on Hyperspectral and LiDAR Data

Expansive species classification with remote sensing techniques offers great support for botanical field works aimed at detection of their distribution within areas of conservation value and assessment of the threat caused to natural habitats. Large number of spectral bands and high spatial resolution allows for identification of particular species. LiDAR (Light Detection and Ranging) data provide information about areas such as vegetation structure. Because the species differ in terms of features during the growing season, it is important to know when their spectral responses are unique in the background of the surrounding vegetation. The aim of the study was to identify two expansive grass species: Molinia caerulea and Calamagrostis epigejos in the Natura 2000 area in Poland depending on the period and dataset used. Field work was carried out during late spring, summer and early autumn, in parallel with remote sensing data acquisition. Airborne 1-m resolution HySpex images and LiDAR data were used. HySpex images were corrected geometrically and atmospherically before Minimum Noise Fraction (MNF) transformation and vegetation indices calculation. Based on a LiDAR point cloud generated Canopy Height Model, vegetation structure from discrete and full-waveform data and topographic indexes were generated. Classifications were performed using a Random Forest algorithm. The results show post-classification maps and their accuracies: Kappa value and F1 score being the harmonic mean of producer (PA) and user (UA) accuracy, calculated iteratively. Based on these accuracies and botanical knowledge, it was possible to assess the best identification date and dataset used for analysing both species. For M. caerulea the highest median Kappa was 0.85 (F1 = 0.89) in August and for C. epigejos 0.65 (F1 = 0.73) in September. For both species, adding discrete or full-waveform LiDAR data improved the results. We conclude that hyperspectral (HS) and LiDAR airborne data could be useful to identify grassland species encroaching into Natura 2000 habitats and for supporting their monitoring.