Olive Tree Biovolume from UAV Multi-Resolution Image Segmentation with Mask R-CNN.

Olive tree growing is an important economic activity in many countries, mostly in the Mediterranean Basin, Argentina, Chile, Australia, and California. Although recent intensification techniques organize olive groves in hedgerows, most olive groves are rainfed and the trees are scattered (as in Spain and Italy, which account for 50% of the world's olive oil production). Accurate measurement of trees biovolume is a first step to monitor their performance in olive production and health. In this work, we use one of the most accurate deep learning instance segmentation methods (Mask R-CNN) and unmanned aerial vehicles (UAV) images for olive tree crown and shadow segmentation (OTCS) to further estimate the biovolume of individual trees. We evaluated our approach on images with different spectral bands (red, green, blue, and near infrared) and vegetation indices (normalized difference vegetation index-NDVI-and green normalized difference vegetation index-GNDVI). The performance of red-green-blue (RGB) images were assessed at two spatial resolutions 3 cm/pixel and 13 cm/pixel, while NDVI and GNDV images were only at 13 cm/pixel. All trained Mask R-CNN-based models showed high performance in the tree crown segmentation, particularly when using the fusion of all dataset in GNDVI and NDVI (F1-measure from 95% to 98%). The comparison in a subset of trees of our estimated biovolume with ground truth measurements showed an average accuracy of 82%. Our results support the use of NDVI and GNDVI spectral indices for the accurate estimation of the biovolume of scattered trees, such as olive trees, in UAV images.

Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors.

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands.

A co-designed method to guide decision-making in protected area visitor centres.

Protected areas (PAs) constitute the largest global effort for biodiversity conservation and the maintenance of ecosystem services. Science-based management, grounded in methods co-designed by scientists and managers, is necessary to improve the efficiency of PAs to achieve these goals and to promote sustainable development. Visitor centres (VCs) in PAs play an important role to facilitate the supply of recreational ecosystem services and to promote environmental awareness. In this study, scientists and managers co-developed a method to assess visitors' perceptions of the recreational activities carried out in VCs and how they depend on the type of visitors. The research was performed at 13 PAs in Andalusia (Spain). A questionnaire that measures users' satisfaction with the services provided by VCs was implemented in two phases: 1) selection of items through the critical incident technique, and 2) validation of the scale by using exploratory and confirmatory factor analysis. The main result is an instrument composed of 18 indicators classified into three dimensions: information, facilities and service received from personnel. The instrument provides additional information useful for managers, such as homogeneity of valuation throughout the PA network and sociocultural factors that may explain the differences in visitors' valuation. The instrument developed could either be used directly or adapted for recreation management in other similar PAs. The proposed methodology can also be reproduced to validate other measurement instruments. This study illustrates how the development of a collaborative research method by scholars and practitioners can improve recreational management in PAs.

The Fate of Endemic Species Specialized in Island Habitat under Climate Change in a Mediterranean High Mountain.

Mediterranean high-mountain endemic species are particularly vulnerable to climatic changes in temperature, precipitation and snow-cover dynamics. Sierra Nevada (Spain) is a biodiversity hotspot in the western Mediterranean, with an enormous plant species richness and endemicity. Moehringia fontqueri is a threatened endemic plant restricted to north-facing siliceous rocks along a few ridges of the eastern Sierra Nevada. To guide conservation actions against climate change effects, here we propose the simultaneous assessment of the current reproductive success and the possible species' range changes between current and future climatic conditions, assessing separately different subpopulations by altitude. Reproductive success was tested through the seed-set data analysis. The species' current habitat suitability was modeled in Maxent using species occurrences, topographic, satellite and climatic variables. Future habitat suitability was carried out for two climatic scenarios (RCP 2.6 and 8.5). The results showed the lowest reproductive success at the lowest altitudes, and vice versa at the highest altitudes. Habitat suitability decreased by 80% from current conditions to the worst-case scenario (RCP 8.5). The lowest subpopulations were identified as the most vulnerable to climate change effects while the highest ones were the nearest to future suitable habitats. Our simultaneous assessment of reproductive success and habitat suitability aims to serve as a model to guide conservation, management and climate change mitigation strategies through adaptive management to safeguard the persistence of the maximum genetic pool of Mediterranean high-mountain plants threatened by climate change.

Sentinel2GlobalLULC: A Sentinel-2 RGB image tile dataset for global land use/cover mapping with deep learning.

Land-Use and Land-Cover (LULC) mapping is relevant for many applications, from Earth system and climate modelling to territorial and urban planning. Global LULC products are continuously developing as remote sensing data and methods grow. However, there still exists low consistency among LULC products due to low accuracy in some regions and LULC types. Here, we introduce Sentinel2GlobalLULC, a Sentinel-2 RGB image dataset, built from the spatial-temporal consensus of up to 15 global LULC maps available in Google Earth Engine. Sentinel2GlobalLULC v2.1 contains 194877 single-class RGB image tiles organized into 29 LULC classes. Each image is a 224 × 224 pixels tile at 10 × 10 m resolution built as a cloud-free composite from Sentinel-2 images acquired between June 2015 and October 2020. Metadata includes a unique LULC annotation per image, together with level of consensus, reverse geo-referencing, global human modification index, and number of dates used in the composite. Sentinel2GlobalLULC is designed for training deep learning models aiming to build precise and robust global or regional LULC maps.

Climate legacies drive the distribution and future restoration potential of dryland forests.

Knowing the extent and environmental drivers of forests is key to successfully restore degraded ecosystems, and to mitigate climate change and desertification impacts using tree planting. Water availability is the main limiting factor for the development of forests in drylands, yet the importance of groundwater resources and palaeoclimate as drivers of their current distribution has been neglected. Here we report that mid-Holocene climates and aquifer trends are key predictors of the distribution of dryland forests worldwide. We also updated the global extent of dryland forests to 1,283 million hectares and showed that failing to consider past climates and aquifers has resulted in ignoring or misplacing up to 130 million hectares of forests in drylands. Our findings highlight the importance of a wetter past and well-preserved aquifers to explain the current distribution of dryland forests, and can guide restoration actions by avoiding unsuitable areas for tree establishment in a drier world.

Evaluating the consistency of the 1982-1999 NDVI trends in the Iberian Peninsula across four time-series derived from the AVHRR sensor: LTDR, GIMMS, FASIR, and PAL-II.

Successive efforts have processed the Advanced Very High Resolution Radiometer (AVHRR) sensor archive to produce Normalized Difference Vegetation Index (NDVI) datasets (i.e., PAL, FASIR, GIMMS, and LTDR) under different corrections and processing schemes. Since NDVI datasets are used to evaluate carbon gains, differences among them may affect nations' carbon budgets in meeting international targets (such as the Kyoto Protocol). This study addresses the consistency across AVHRR NDVI datasets in the Iberian Peninsula (Spain and Portugal) by evaluating whether their 1982-1999 NDVI trends show similar spatial patterns. Significant trends were calculated with the seasonal Mann-Kendall trend test and their spatial consistency with partial Mantel tests. Over 23% of the Peninsula (N, E, and central mountain ranges) showed positive and significant NDVI trends across the four datasets and an additional 18% across three datasets. In 20% of Iberia (SW quadrant), the four datasets exhibited an absence of significant trends and an additional 22% across three datasets. Significant NDVI decreases were scarce (croplands in the Guadalquivir and Segura basins, La Mancha plains, and Valencia). Spatial consistency of significant trends across at least three datasets was observed in 83% of the Peninsula, but it decreased to 47% when comparing across the four datasets. FASIR, PAL, and LTDR were the most spatially similar datasets, while GIMMS was the most different. The different performance of each AVHRR dataset to detect significant NDVI trends (e.g., LTDR detected greater significant trends (both positive and negative) and in 32% more pixels than GIMMS) has great implications to evaluate carbon budgets. The lack of spatial consistency across NDVI datasets derived from the same AVHRR sensor archive, makes it advisable to evaluate carbon gains trends using several satellite datasets and, whether possible, independent/additional data sources to contrast.

FloraSNevada: a trait database of the vascular flora of Sierra Nevada, southeast Spain.

Providing a complete data set with species and trait information for a given area is essential for assessing plant conservation, management, and ecological restoration, for both local and global applications. Also, these data sets provide additional information for surveys or data collections, establishing the starting point for more detailed studies on plant evolution, vegetation dynamics, and vegetation responses to disturbance and management. This data base covers Sierra Nevada mountains (southeastern Spain), a recognized plant biodiversity hotspot within the Mediterranean context. According to previous available data (before this augmented compilation), these mountains host 7% of the 24,000 Mediterranean vascular plants, despite covering just 0.01% of its area. Another characteristic of the Sierra Nevada is the great singularity of its flora, with 95 taxa being endemic to the high-mountain area of Sierra Nevada and surroundings. From these endemic taxa, 70% are endangered by different threats, global warming being a leading cause. We seek to provide a complete and updated database of the flora of the Sierra Nevada mountains (southeast Spain). The goal of the present data set is to compile the names of all the vascular plant taxa inhabiting Sierra Nevada, together with relevant features including taxonomical, morphological-ecological traits, distribution, habitats, abundance, and conservation status. The data were compiled according to all the available information sources on taxonomy, ecology, and plant-species distribution. The resulting data set includes 2,348 taxa belonging to 1,937 species, 377 subspecies, and 34 hybrids, from a total of 756 genera and 146 families represented in the collection. For each taxa, together with taxonomical information (Phylum, Class, Family, Genus, Taxa), we compiled plant traits (life form, spinescence, flower symmetry, flower sexuality, plant gender, androecium:ginoecium ratio, flower color, perianth type, pollinator type, flowering, seed dispersal, and vegetative reproduction), and their environmental association (origin, endemic character, general distribution, substrate, elevation, habitat, local abundance, hygrophilous behavior, and conservation status). All these traits were compiled from all the available information sources, resulting in a complete and updated database for Sierra Nevada vascular flora. This data set provides valuable information on plant traits in an outstanding micro hotspot within the Mediterranean hotspot. This data set can be freely used for noncommercial purposes. This data set is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). When you use this data set, we request that you cite the data and this data paper.

Evaluating tourist profiles and nature-based experiences in Biosphere Reserves using Flickr: Matches and mismatches between online social surveys and photo content analysis.

Monitoring visitor dynamics and their nature-based experiences is an important dimension in the conservation management of protected areas. In the current digital age, the content analysis of social media information is being increasingly used in such a context. However, research testing whether social media content analysis provides similar information to that obtained from stated preference methods is lacking. We aimed to identify differences in the classification of tourist profiles and nature-based experiences, both from online social surveys and photo content analysis. Our approach targeted Flickr's social media users visiting two Biosphere Reserves in Southern Europe: Doñana and Sierra Nevada. We manually classified the main content of Flickr photos considering different categories of tourist profiles and nature-based experiences. Concurrently, we distributed online surveys to Flickr users responsible for those photos and gathered their self-stated classification of tourist profiles and experiences. Finally, we compared the classification results from both content analysis and online surveys using multiple congruence metrics and tests. Overall, we found both matches and mismatches between the results from content analysis and online surveys depending on the categories of tourist profiles and their experiences. "Landscape and species" was the only category with consistent matches between content analysis and online surveys for both tourist profiles and nature-based experiences. We suggest that conclusions based on content analysis or online surveys alone can lead to incomplete information. Instead, the adoption of both content analysis and online surveys should provide complementary perspectives for the monitoring of nature's cultural capital.

Use of descriptors of ecosystem functioning for monitoring a national park network: a remote sensing approach.

Baseline assessments and monitoring of protected areas are essential for making management decisions, evaluating the effectiveness of management practices, and tracking the effects of global changes. For these purposes, the analysis of functional attributes of ecosystems (i.e., different aspects of the exchange of matter and energy) has advantages over the traditional use of structural attributes, like a quicker response to disturbances and the fact that they are easily monitored through remote sensing. In this study, we described the spatiotemporal patterns of different aspects of the ecosystem functioning of the Spanish national parks and their response to environmental changes between 1982 and 2006. To do so, we used the NOAA/AVHRR-GIMMS dataset of the Normalized Difference Vegetation Index (NDVI), a linear estimator of the fraction of photosynthetic active radiation intercepted by vegetation, which is the main control of carbon gains. Nearly all parks have significantly changed during the last 25 years: The radiation interception has increased, the contrast between the growing and nongrowing seasons has diminished, and the dates of maximum and minimum interception have advanced. Some parks concentrated more changes than others and the degree of change varied depending on their different environmental conditions, management, and conservation histories. Our approach identified reference conditions and temporal changes for different aspects of ecosystem functioning, which can be used for management purposes of protected areas in response to global changes.

Effects of species traits and environmental predictors on performance and transferability of ecological niche models.

The ability of ecological niche models (ENMs) to produce robust predictions for different time frames (i.e. temporal transferability) may be hindered by a lack of ecologically relevant predictors. Model performance may also be affected by species traits, which may reflect different responses to processes controlling species distribution. In this study, we tested four primary hypotheses involving the role of species traits and environmental predictors in ENM performance and transferability. We compared the predictive accuracy of ENMs based upon (1) climate, (2) land-use/cover (LULC) and (3) ecosystem functional attributes (EFAs), and (4) the combination of these factors for 27 bird species within and beyond the time frame of model calibration. The combination of these factors significantly increased both model performance and transferability, highlighting the need to integrate climate, LULC and EFAs to improve biodiversity projections. However, the overall model transferability was low (being only acceptable for less than 25% of species), even under a hierarchical modelling approach, which calls for great caution in the use of ENMs to predict bird distributions under global change scenarios. Our findings also indicate that positive effects of species traits on predictive accuracy within model calibration are not necessarily translated into higher temporal transferability.

Whale counting in satellite and aerial images with deep learning.

Despite their interest and threat status, the number of whales in world's oceans remains highly uncertain. Whales detection is normally carried out from costly sighting surveys, acoustic surveys or through high-resolution images. Since deep convolutional neural networks (CNNs) are achieving great performance in several computer vision tasks, here we propose a robust and generalizable CNN-based system for automatically detecting and counting whales in satellite and aerial images based on open data and tools. In particular, we designed a two-step whale counting approach, where the first CNN finds the input images with whale presence, and the second CNN locates and counts each whale in those images. A test of the system on Google Earth images in ten global whale-watching hotspots achieved a performance (F1-measure) of 81% in detecting and 94% in counting whales. Combining these two steps increased accuracy by 36% compared to a baseline detection model alone. Applying this cost-effective method worldwide could contribute to the assessment of whale populations to guide conservation actions. Free and global access to high-resolution imagery for conservation purposes would boost this process.

Assessing the multi-scale predictive ability of ecosystem functional attributes for species distribution modelling.

Global environmental changes are rapidly affecting species' distributions and habitat suitability worldwide, requiring a continuous update of biodiversity status to support effective decisions on conservation policy and management. In this regard, satellite-derived Ecosystem Functional Attributes (EFAs) offer a more integrative and quicker evaluation of ecosystem responses to environmental drivers and changes than climate and structural or compositional landscape attributes. Thus, EFAs may hold advantages as predictors in Species Distribution Models (SDMs) and for implementing multi-scale species monitoring programs. Here we describe a modelling framework to assess the predictive ability of EFAs as Essential Biodiversity Variables (EBVs) against traditional datasets (climate, land-cover) at several scales. We test the framework with a multi-scale assessment of habitat suitability for two plant species of conservation concern, both protected under the EU Habitats Directive, differing in terms of life history, range and distribution pattern (Iris boissieri and Taxus baccata). We fitted four sets of SDMs for the two test species, calibrated with: interpolated climate variables; landscape variables; EFAs; and a combination of climate and landscape variables. EFA-based models performed very well at the several scales (AUCmedian from 0.881±0.072 to 0.983±0.125), and similarly to traditional climate-based models, individually or in combination with land-cover predictors (AUCmedian from 0.882±0.059 to 0.995±0.083). Moreover, EFA-based models identified additional suitable areas and provided valuable information on functional features of habitat suitability for both test species (narrowly vs. widely distributed), for both coarse and fine scales. Our results suggest a relatively small scale-dependence of the predictive ability of satellite-derived EFAs, supporting their use as meaningful EBVs in SDMs from regional and broader scales to more local and finer scales. Since the evaluation of species' conservation status and habitat quality should as far as possible be performed based on scalable indicators linking to meaningful processes, our framework may guide conservation managers in decision-making related to biodiversity monitoring and reporting schemes.

Managing plant invasions through the lens of remote sensing: A review of progress and the way forward.

Biological invasions are a challenging driver of global environmental change and a fingerprint of the Anthropocene. Remote sensing has gradually become a fundamental tool for understanding invasion patterns, processes and impacts. Nevertheless, a quantitative overview of the progress and extent of remote sensing applications to the management of plant invasions is lacking. This overview is particularly necessary to support the development of more operational frameworks based on remote sensing that can effectively improve the management of invasions. Here, we evaluate and discuss the progress, current state and future opportunities of remote sensing for the research and management of plant invasions. Supported on a systematic literature review, our study shows that, since the 1970s, remote sensing was mainly used to map and identify invasive plants, evolving, around the mid-2000s, towards a tool for assessing invasion impacts. Although remote sensing studies often focus on detecting plant invaders at advanced invasion stages, they can also contribute to the prediction of early invasion stages and to the assessment of their impacts. Despite the growing awareness of technical limitations, remote sensing offers many opportunities to further improve the management of plant invasions. These opportunities relate to the capacity of remote sensing to: (a) detect and evaluate the extent of invasions, assisting on any management option aiming at mitigating plant invasions and their impacts; (b) consider modelling frameworks that anticipate future invasions, supporting the prevention and eradication at early invasion stages and protecting ecosystems and the services they provide; and (c) monitor changes in invasion dominance, as well as the resulting impacts, supporting mitigation, restoration and adaptation actions. Finally, we discuss the way forward to make remote sensing more effective in the scope of invasion management, considering current and future Earth observation missions.

Remote-sensing based approach to forecast habitat quality under climate change scenarios.

As climate change is expected to have a significant impact on species distributions, there is an urgent challenge to provide reliable information to guide conservation biodiversity policies. In addressing this challenge, we propose a remote sensing-based approach to forecast the future habitat quality for European badger, a species not abundant and at risk of local extinction in the arid environments of southeastern Spain, by incorporating environmental variables related with the ecosystem functioning and correlated with climate and land use. Using ensemble prediction methods, we designed global spatial distribution models for the distribution range of badger using presence-only data and climate variables. Then, we constructed regional models for an arid region in the southeast Spain using EVI (Enhanced Vegetation Index) derived variables and weighting the pseudo-absences with the global model projections applied to this region. Finally, we forecast the badger potential spatial distribution in the time period 2071-2099 based on IPCC scenarios incorporating the uncertainty derived from the predicted values of EVI-derived variables. By including remotely sensed descriptors of the temporal dynamics and spatial patterns of ecosystem functioning into spatial distribution models, results suggest that future forecast is less favorable for European badgers than not including them. In addition, change in spatial pattern of habitat suitability may become higher than when forecasts are based just on climate variables. Since the validity of future forecast only based on climate variables is currently questioned, conservation policies supported by such information could have a biased vision and overestimate or underestimate the potential changes in species distribution derived from climate change. The incorporation of ecosystem functional attributes derived from remote sensing in the modeling of future forecast may contribute to the improvement of the detection of ecological responses under climate change scenarios.