Modelling the area of occupancy of habitat types with remote sensing

Drivers of habitat availability for terrestrial mammals: Unravelling the role of livestock, land conversion and intrinsic traits in the past 50 years

The global decline of terrestrial species is largely due to the degradation, loss and fragmentation of their habitats. The conversion of natural ecosystems for cropland, rangeland, forest products and human infrastructure are the primary causes of habitat deterioration. Due to the paucity of data on the past distribution of species and the scarcity of fine-scale habitat conversion maps, however, accurate assessment of the recent effects of habitat degradation, loss and fragmentation on the range of mammals has been near impossible. We aim to assess the proportions of available habitat within the lost and retained parts of mammals' distribution ranges, and to identify the drivers of habitat availability. We produced distribution maps for 475 terrestrial mammals for the range they occupied 50 years ago and compared them to current range maps. We then calculated the differences in the percentage of 'area of habitat' (habitat available to a species within its range) between the lost and retained range areas. Finally, we ran generalized linear mixed models to identify which variables were more influential in determining habitat availability in the lost and retained parts of the distribution ranges. We found that 59% of species had a lower proportion of available habitat in the lost range compared to the retained range, thus hypothesizing that habitat loss could have contributed to range declines. The most important factors negatively affecting habitat availability were the conversion of land to rangeland and high density of livestock. Significant intrinsic traits were those related to reproductive timing and output, habitat breadth and medium body size. Our findings emphasize the importance of implementing conservation strategies to mitigate the impacts caused by human activities on the habitats of mammals, and offer evidence indicating which species have the potential to reoccupy portions of their former range if other threats cease to occur.

A national-scale assessment of land use change in peatlands between 1989 and 2020 using Landsat data and Google Earth Engine-a case study of Ireland

Over the centuries, anthropogenic pressure has severely impacted peatlands on the European continent. Peatlands cover ~ 21% (1.46 Mha) of Ireland's land surface, but 85% have been degraded due to management activities (land use). Ireland needs to meet its 2030 climate energy framework targets related to greenhouse gas (GHG) emissions from land use, land use change and forestry, including wetlands. Despite Ireland's voluntary decision to include peatlands in this system in 2020, information on land use activities and associated GHG emissions from peatlands is lacking. This study strives to fill this information gap by using Landsat (5, 8) data with Google Earth Engine and machine learning to examine and quantify land use on Irish peatlands across three time periods: 1990, 2005 and 2019. Four peatland land use classes were mapped and assessed: industrial peat extraction, forestry, grassland and residual peatland. The overall accuracy of the classification was 86% and 85% for the 2005 and 2019 maps, respectively. The accuracy of the 1990 dataset could not be assessed due to the unavailability of high-resolution reference data. The results indicate that extensive management activities have taken place in peatlands over the past three decades, which may have negative impacts on its ecological integrity and the many ecosystem services provided. By utilising cloud computing, temporal mosaicking and Landsat data, this study developed a robust methodology that overcomes cloud contamination and produces the first peatland land use maps of Ireland with wall-to-wall coverage. This has the potential for regional and global applications, providing maps that could help understand unsustainable management practices on peatlands and the impact on GHG emissions.

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.

Translating habitat class to land cover to map area of habitat of terrestrial vertebrates

Area of habitat (AOH) is defined as the "habitat available to a species, that is, habitat within its range" and is calculated by subtracting areas of unsuitable land cover and elevation from the range. The International Union for the Conservation of Nature (IUCN) Habitats Classification Scheme provides information on species habitat associations, and typically unvalidated expert opinion is used to match habitat to land-cover classes, which generates a source of uncertainty in AOH maps. We developed a data-driven method to translate IUCN habitat classes to land cover based on point locality data for 6986 species of terrestrial mammals, birds, amphibians, and reptiles. We extracted the land-cover class at each point locality and matched it to the IUCN habitat class or classes assigned to each species occurring there. Then, we modeled each land-cover class as a function of IUCN habitat with (SSG, using) logistic regression models. The resulting odds ratios were used to assess the strength of the association between each habitat and land-cover class. We then compared the performance of our data-driven model with those from a published translation table based on expert knowledge. We calculated the association between habitat classes and land-cover classes as a continuous variable, but to map AOH as binary presence or absence, it was necessary to apply a threshold of association. This threshold can be chosen by the user according to the required balance between omission and commission errors. Some habitats (e.g., forest and desert) were assigned to land-cover classes with more confidence than others (e.g., wetlands and artificial). The data-driven translation model and expert knowledge performed equally well, but the model provided greater standardization, objectivity, and repeatability. Furthermore, our approach allowed greater flexibility in the use of the results and uncertainty to be quantified. Our model can be modified for regional examinations and different taxonomic groups.

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.

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.

Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping

In the light of the “Biological Diversity” concept, habitats are cardinal pieces for biodiversity quantitative estimation at a local and global scale. In Europe EUNIS (European Nature Information System) is a system tool for habitat identification and assessment. Earth Observation (EO) data, which are acquired by satellite sensors, offer new opportunities for environmental sciences and they are revolutionizing the methodologies applied. These are providing unprecedented insights for habitat monitoring and for evaluating the Sustainable Development Goals (SDGs) indicators. This paper shows the results of a novel approach for a spatially explicit habitat mapping in Italy at a national scale, using a supervised machine learning model (SMLM), through the combination of vegetation plot database (as response variable), and both spectral and environmental predictors. The procedure integrates forest habitat data in Italy from the European Vegetation Archive (EVA), with Sentinel-2 imagery processing (vegetation indices time series, spectral indices, and single bands spectral signals) and environmental data variables (i.e., climatic and topographic), to parameterize a Random Forests (RF) classifier. The obtained results classify 24 forest habitats according to the EUNIS III level: 12 broadleaved deciduous (T1), 4 broadleaved evergreen (T2) and eight needleleaved forest habitats (T3), and achieved an overall accuracy of 87% at the EUNIS II level classes (T1, T2, T3), and an overall accuracy of 76.14% at the EUNIS III level. The highest overall accuracy value was obtained for the broadleaved evergreen forest equal to 91%, followed by 76% and 68% for needleleaved and broadleaved deciduous habitat forests, respectively. The results of the proposed methodology open the way to increase the EUNIS habitat categories to be mapped together with their geographical extent, and to test different semi-supervised machine learning algorithms and ensemble modelling methods.

The Role of Remote Sensing Data in Habitat Suitability and Connectivity Modeling: Insights from the Cantabrian Brown Bear

Ecological modeling requires sufficient spatial resolution and a careful selection of environmental variables to achieve good predictive performance. Although national and international administrations offer fine-scale environmental data, they usually have limited spatial coverage (country or continent). Alternatively, optical and radar satellite imagery is available with high resolutions, global coverage and frequent revisit intervals. Here, we compared the performance of ecological models trained with free satellite data with models fitted using regionally restricted spatial datasets. We developed brown bear habitat suitability and connectivity models from three datasets with different spatial coverage and accessibility. These datasets comprised (1) a Sentinel-1 and 2 land cover map (global coverage); (2) pan-European vegetation and land cover layers (continental coverage); and (3) LiDAR data and the Forest Map of Spain (national coverage). Results show that Sentinel imagery and pan-European datasets are powerful sources to estimate vegetation variables for habitat and connectivity modeling. However, Sentinel data could be limited for understanding precise habitat–species associations if the derived discrete variables do not distinguish a wide range of vegetation types. Therefore, more effort should be taken to improving the thematic resolution of satellite-derived vegetation variables. Our findings support the application of ecological modeling worldwide and can help select spatial datasets according to their coverage and resolution for habitat suitability and connectivity modeling.

Spatial distribution of stygobitic crustacean harpacticoids at the boundaries of groundwater habitat types in Europe

The distribution patterns of stygobitic crustacean harpacticoids at the boundaries of three different groundwater habitat types in Europe were analysed through a GIS proximity analysis and fitted to exponential models. The results showed that the highest frequency of occurrences was recorded in aquifers in consolidated rocks, followed by the aquifers in unconsolidated sediments and, finally, by the practically non-aquiferous rocks. The majority of the stygobitic harpacticoid species were not able to disperse across the boundaries between two adjacent habitats, with 66% of the species occurring in a single habitat type. The species were not evenly distributed, and 35–69% of them occurred from 2 to 6 km to the boundaries, depending on the adjacent habitat types. The distribution patterns were shaped by features extrinsic to the species, such as the hydrogeological properties of the aquifers, and by species’ intrinsic characteristics such as the preference for a given habitat type and dispersal abilities. Most boundaries between adjacent habitat types resulted to be “breaches”, that is transmissive borders for stygobitic harpacticoids, while others were “impermeable walls”, that is absorptive borders. Our results suggest that conservation measures of groundwater harpacticoids should consider how species are distributed within the different groundwater habitat types and at their boundaries to ensure the preservation of species metapopulations within habitat patches and beyond them.

Relationship of NDVI and oak (Quercus) pollen including a predictive model in the SW Mediterranean region

Techniques of remote sensing are being used to develop phenological studies. Our goal is to study the correlation among the Normalized Difference Vegetation Index (NDVI) related with oak trees included in three set data polygons (15, 25 and 50 km to aerobiological sampling point as NDVI-15, 25 and 50), and oak (Quercus) daily average pollen counts from 1994 to 2013. The study was developed in the SW Mediterranean region with continuous pollen recording within the mean pollen season of each studied year. These pollen concentrations were compared with NDVI values in the locations containing the vegetation under a study based on two cartographic sources: the Extremadura Forest Map (MFEx) of Spain and the Fifth National Forest Inventory (IFN5) from Portugal. The importance of this work is to propose the relationship among data related in space and time by Spearman and Granger causality tests. 9 out of 20 studied years have shown significant results with the Granger causality test between NDVI and pollen concentration, and in 12 years, significant values were obtained by Spearman test. The distances of influence on the contribution of Quercus pollen to the sampler showed statistically significant results depending on the year. Moreover, a predictive model by using Artificial Neural Network (ANN) was applied with better results in NDVI25 than for NDVI15 or NDVI50. The addition of NDVI25 with the lag of 5 days and some weather parameters in the model was applied with a RMSE of 4.26 (Spearman coefficient r = 0.77) between observed and predicted values. Based on these results, NDVI seems to be a useful parameter to predict airborne pollen.

High-Resolution Vegetation Mapping Using eXtreme Gradient Boosting Based on Extensive Features

Accurate mapping of vegetation is a premise for conserving, managing, and sustainably using vegetation resources, especially in conditions of intensive human activities and accelerating global changes. However, it is still challenging to produce high-resolution multiclass vegetation map in high accuracy, due to the incapacity of traditional mapping techniques in distinguishing mosaic vegetation classes with subtle differences and the paucity of fieldwork data. This study created a workflow by adopting a promising classifier, extreme gradient boosting (XGBoost), to produce accurate vegetation maps of two strikingly different cases (the Dzungarian Basin in China and New Zealand) based on extensive features and abundant vegetation data. For the Dzungarian Basin, a vegetation map with seven vegetation types, 17 subtypes, and 43 associations was produced with an overall accuracy of 0.907, 0.801, and 0.748, respectively. For New Zealand, a map of 10 habitats and a map of 41 vegetation classes were produced with 0.946, and 0.703 overall accuracy, respectively. The workflow incorporating simplified field survey procedures outperformed conventional field survey and remote sensing based methods in terms of accuracy and efficiency. In addition, it opens a possibility of building large-scale, high-resolution, and timely vegetation monitoring platforms for most terrestrial ecosystems worldwide with the aid of Google Earth Engine and citizen science programs.

Climate change induced range shifts in seaweeds distributions in Europe

There are evidences of how climate change is affecting seaweeds distribution and the ecosystems services they provide. Therefore, it is necessary to consider these impacts when managing marine areas. One of the most applied tools in recent years to deal with this are species distribution models, however there are still some challenges to solve, such as the inclusion of hydrodynamic predictors and the application of effective, transferable and user-oriented methodologies. Five species (Saccorhiza polyschides, Gelidium spinosum, Sargassum muticum, Pelvetia canaliculata and Cystoseira baccata) in Europe and 15 variables were considered. Nine of them were projected to the RCPs 4.5 and 8.5 for the mid-term (2040-2069) and the long term (2070-2099). Algorithms for each species were applied to generate models that were assessed by comparison of probabilities and observations (area under the curve, true skill statistics, Boyce index, sensitivity, correct classification rate), niches overlap (Schoener's D, Hellinger's I), geographical similarity (interquartile range) and ecological realism. Models built demonstrated very good predictive accuracy and sensitivity, without overfitting risk. A medium overlap in the historical and RCPs environmental conditions were obtained, therefore the models can be considered transferable and results accurate because only some isolated points were detected as outliers, corresponding to low probabilities. The areas of S. polyschides and G. spinosum have been identified to be dramatically reduced, meanwhile S. muticum and C. baccata were predicted to expand their range. P. canaliculata was expected to keep its sites of presence but with a decrease in its probability of occurrence. For all species it was remarkable the importance of hydrodynamic variables and parameters representing extreme conditions. Spatially predictions of the potential species and areas at risk are decisive for defining management strategies and resource allocation. The performance and usefulness of the approach applied in this study have been demonstrated for algae with different ecological requirements (from upper littoral to subtidal) and distributional patterns (native and invasive), therefore results can be used by marine planners with different goals: marine protected areas designation, monitoring efforts guiding, invasions risk assessment or aquaculture facilities zonation.

Evidences for a shared history for spectacled salamanders, haplotypes and climate

The so-called glacial refugia, formed during the Pleistocene climatic oscillations, played a major role in shaping the distribution of European species, triggering migrations or isolating populations. Many of these events were recently investigated by genetic data, mainly for the European Last Glacial stage, in the Iberic, Italian and Greek-Balkan peninsulas. The amphibian genus Salamandrina, the most ancient living salamandrid lineage, was widespread in Europe until the climatic oscillations of Miocene probably forced it to shelter in the only suitable territory at that time, the Apennines. Nowadays this genus is endemic of peninsular Italy with two parapatric species, S. perspicillata and S. terdigitata, sharing an area of secondary contact formed after the Last Glacial Maximum. Climate is generally identified as the key factor for the interpretation of genetic data. In this research, we directly measure climate influences on the two Salamandrina known species through Ensemble Modelling techniques and post-modelling GIS analyses, integrating updated genetic data in this process. Our results confirm the hypotheses of southwards (and subsequent northwards) shifts, identify glacial refugia and corridors used for the post-glacial re-colonization. Finally, we map a contact zone deserving more sampling effort to disentangle the introgression and hybridization observed.