Better together: Integrating and fusing multispectral and radar satellite imagery to inform biodiversity monitoring, ecological research and conservation science

A new data-driven paradigm for the study of avian migratory navigation

Avian navigation has fascinated researchers for many years. Yet, despite a vast amount of literature on the topic it remains a mystery how birds are able to find their way across long distances while relying only on cues available locally and reacting to those cues on the fly. Navigation is multi-modal, in that birds may use different cues at different times as a response to environmental conditions they find themselves in. It also operates at different spatial and temporal scales, where different strategies may be used at different parts of the journey. This multi-modal and multi-scale nature of navigation has however been challenging to study, since it would require long-term tracking data along with contemporaneous and co-located information on environmental cues. In this paper we propose a new alternative data-driven paradigm to the study of avian navigation. That is, instead of taking a traditional theory-based approach based on posing a research question and then collecting data to study navigation, we propose a data-driven approach, where large amounts of data, not purposedly collected for a specific question, are analysed to identify as-yet-unknown patterns in behaviour. Current technological developments have led to large data collections of both animal tracking data and environmental data, which are openly available to scientists. These open data, combined with a data-driven exploratory approach using data mining, machine learning and artificial intelligence methods, can support identification of unexpected patterns during migration, and lead to a better understanding of multi-modal navigational decision-making across different spatial and temporal scales.

Beyond traditional methods: Innovative integration of LISS IV and Sentinel 2A imagery for unparalleled insight into Himalayan ibex habitat suitability

The utilization of satellite images in conservation research is becoming more prevalent due to advancements in remote sensing technologies. To achieve accurate classification of wildlife habitats, it is important to consider the different capabilities of spectral and spatial resolution. Our study aimed to develop a method for accurately classifying habitat types of the Himalayan ibex (Capra sibirica) using satellite data. We used LISS IV and Sentinel 2A data to address both spectral and spatial issues. Furthermore, we integrated the LISS IV data with the Sentinel 2A data, considering their individual geometric information. The Random Forest approach outperformed other algorithms in supervised classification techniques. The integrated image had the highest level of accuracy, with an overall accuracy of 86.17% and a Kappa coefficient of 0.84. Furthermore, to delineate the suitable habitat for the Himalayan ibex, we employed ensemble modelling techniques that incorporated Land Cover Land Use data from LISS IV, Sentinel 2A, and Integrated image, separately. Additionally, we incorporated other predictors including topographical features, soil and water radiometric indices. The integrated image demonstrated superior accuracy in predicting the suitable habitat for the species. The identification of suitable habitats was found to be contingent upon the consideration of two key factors: the Soil Adjusted Vegetation Index and elevation. The study findings are important for advancing conservation measures. Using accurate classification methods helps identify important landscape components. This study offers a novel and important approach to conservation planning by accurately categorising Land Cover Land Use and identifying critical habitats for the species.

Madagascar's burned area from Sentinel-2 imagery (2016-2022): Four times higher than from lower resolution sensors

Madagascar is one of the most burned regions in the world, to the point that it has been called the 'Isle of fire' or the 'Burning Island'. An accurate characterization of the burned area (BA) is crucial for understanding the true situation and impacts of fires on this island, where there is an active scientific debate on how fire affects multiple environmental and socioeconomic aspects, and how fire regimes should be in a complex context with differing interests. Despite this, recent advances have revealed that BA in Madagascar is poorly characterised by the currently available global BA products. In this work, we present, validate, and explore a BA database at 20 m spatial resolution for Madagascar covering the period 2016-2022. The database was built based on 75,010 Sentinel-2 images using a two-phase BA detection algorithm. The validation with independent long-term reference units showed Dice coefficients ≥79 %, omission errors ≤24 %, commission errors ≤18 %, and a relative bias ≥ - 8 %. An intercomparison with other available global BA products (GABAM, FireCCI51, C3SBA11, or MCD64) demonstrated that our product (i) exhibits temporal consistency, (ii) represents a significant accuracy improvement, as it reduces BA underestimations by about eightfold, (iii) yields BA estimates four times higher, and (iv) shows enhanced capability in detecting fires of all sizes. The observed BA spatial patterns were heterogeneous across the island, with 32 % of the grasslands burning annually, in contrast to other land cover types such as the dense tropical forest where <2 % burned every year. We conclude that the BA characterization in Madagascar must be addressed using imagery at spatial resolution higher than MODIS or Sentinel-3 (≥250 m), and temporal resolution higher than Landsat (16 days) to deal with cloudiness, the rapid attenuation of burn scars signals, and small fire patches.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

The development of an unsupervised hierarchical clustering analysis of dual-polarization weather surveillance radar observations to assess nocturnal insect abundance and diversity

Contemporary analyses of insect population trends are based, for the most part, on a large body of heterogeneous and short-term datasets of diurnal species that are representative of limited spatial domains. This makes monitoring changes in insect biomass and biodiversity difficult. What is needed is a method for monitoring that provides a consistent, high-resolution picture of insect populations through time over large areas during day and night. Here, we explore the use of X-band weather surveillance radar (WSR) for the study of local insect populations using a high-quality, multi-week time series of nocturnal moth light trapping data. Specifically, we test the hypotheses that (i) unsupervised data-driven classification algorithms can differentiate meteorological and biological phenomena, (ii) the diversity of the classes of bioscatterers are quantitatively related to the diversity of insects as measured on the ground and (iii) insect abundance measured at ground level can be predicted quantitatively based on dual-polarization Doppler WSR variables. Adapting the quasi-vertical profile analysis method and data clustering techniques developed for the analysis of hydrometeors, we demonstrate that our bioscatterer classification algorithm successfully differentiates bioscatterers from hydrometeors over a large spatial scale and at high temporal resolutions. Furthermore, our results also show a clear relationship between biological and meteorological scatterers and a link between the abundance and diversity of radar-based bioscatterer clusters and that of nocturnal aerial insects. Thus, we demonstrate the potential utility of this approach for landscape scale monitoring of biodiversity.

Combining Multispectral and Radar Imagery with Machine Learning Techniques to Map Intertidal Habitats for Migratory Shorebirds

Migratory shorebirds are notable consumers of benthic invertebrates on intertidal sediments. The distribution and abundance of shorebirds will strongly depend on their prey and on landscape and sediment features such as mud and surface water content, topography, and the presence of ecosystem engineers. An understanding of shorebird distribution and ecology thus requires knowledge of the various habitat types which may be distinguished in intertidal areas. Here, we combine Sentinel-1 and Sentinel-2 imagery and a digital elevation model (DEM), using machine learning techniques to map intertidal habitat types of importance to migratory shorebirds and their benthic prey. We do this on the third most important non-breeding area for migratory shorebirds in the East Atlantic Flyway, in the Bijagós Archipelago in West Africa. Using pixel-level random forests, we successfully mapped rocks, shell beds, and macroalgae and distinguished between areas of bare sediment and areas occupied by fiddler crabs, an ecosystem engineer that promotes significant bioturbation on intertidal flats. We also classified two sediment types (sandy and mixed) within the bare sediment and fiddler crab areas, according to their mud content. The overall classification accuracy was 82%, and the Kappa Coefficient was 73%. The most important predictors were elevation, the Sentinel-2-derived water and moisture indexes, and Sentinel-1 VH band. The association of Sentinel-2 with Sentinel-1 and a DEM produced the best results compared to the models without these variables. This map provides an overall picture of the composition of the intertidal habitats in a site of international importance for migratory shorebirds. Most of the intertidal flats of the Bijagós Archipelago are covered by bare sandy sediments (59%), and ca. 22% is occupied by fiddler crabs. This likely has significant implications for the spatial arrangement of the shorebird and benthic invertebrate communities due to the ecosystem engineering by the fiddler crabs, which promotes two vastly different intertidal species assemblages. This large-scale mapping provides an important product for the future monitoring of this high biodiversity area, particularly for ecological research related to the distribution and feeding ecology of the shorebirds and their prey. Such information is key from a conservation and management perspective. By delivering a successful and comprehensive mapping workflow, we contribute to the filling of the current knowledge gap on the application of remote sensing and machine learning techniques within intertidal areas, which are among the most challenging environments to map using remote sensing techniques.

Monitoring rewilding from space: The Knepp estate as a case study

Rewilding is increasingly considered as an option for environmental regeneration, with potential for enhancing both biodiversity and ecosystem services. So far, however, there is little practical information on how to gauge the benefits and limitations of rewilding schemes on ecosystem composition, structure and functioning. To address this knowledge gap, we explored how satellite remote sensing can contribute to informing the monitoring and evaluation of rewilding projects, using the Knepp estate as a case study. To our knowledge, this study is the first to assess the impacts of rewilding as an ecological regeneration strategy on landscape structure and functioning over several decades. Results show significant changes in land cover distribution over the past 20 years inside rewilded areas in the Knepp estate, with a 41.4% decrease in areas with brown agriculture and grass, a roughly sixfold increase in areas covered with shrubs, and a 40.9% increase in areas with trees; vegetation in the rewilded areas also showed a widespread increase in annual primary productivity. Changes in land cover and primary productivity are particularly pronounced in the part of the estate that began its rewilding journey with a period of large herbivore absence. Altogether, our approach clearly demonstrates how freely available satellite data can (1) provide vital insights about long-term changes in ecosystem composition, structure and functioning, even for small, heterogeneous and relatively intensively used landscapes; and (2) help deepen our understanding of the impacts of rewilding on vegetation distribution and dynamics, in ways that complement existing ground-based studies on the impacts of this approach on ecological communities.

Predicting species distributions and community composition using satellite remote sensing predictors

Biodiversity is rapidly changing due to changes in the climate and human related activities; thus, the accurate predictions of species composition and diversity are critical to developing conservation actions and management strategies. In this paper, using satellite remote sensing products as covariates, we constructed stacked species distribution models (S-SDMs) under a Bayesian framework to build next-generation biodiversity models. Model performance of these models was assessed using oak assemblages distributed across the continental United States obtained from the National Ecological Observatory Network (NEON). This study represents an attempt to evaluate the integrated predictions of biodiversity models-including assemblage diversity and composition-obtained by stacking next-generation SDMs. We found that applying constraints to assemblage predictions, such as using the probability ranking rule, does not improve biodiversity prediction models. Furthermore, we found that independent of the stacking procedure (bS-SDM versus pS-SDM versus cS-SDM), these kinds of next-generation biodiversity models do not accurately recover the observed species composition at the plot level or ecological-community scales (NEON plots are 400 m2). However, these models do return reasonable predictions at macroecological scales, i.e., moderately to highly correct assignments of species identities at the scale of NEON sites (mean area ~ 27 km2). Our results provide insights for advancing the accuracy of prediction of assemblage diversity and composition at different spatial scales globally. An important task for future studies is to evaluate the reliability of combining S-SDMs with direct detection of species using image spectroscopy to build a new generation of biodiversity models that accurately predict and monitor ecological assemblages through time and space.

A new method to control error rates in automated species identification with deep learning algorithms

Processing data from surveys using photos or videos remains a major bottleneck in ecology. Deep Learning Algorithms (DLAs) have been increasingly used to automatically identify organisms on images. However, despite recent advances, it remains difficult to control the error rate of such methods. Here, we proposed a new framework to control the error rate of DLAs. More precisely, for each species, a confidence threshold was automatically computed using a training dataset independent from the one used to train the DLAs. These species-specific thresholds were then used to post-process the outputs of the DLAs, assigning classification scores to each class for a given image including a new class called “unsure”. We applied this framework to a study case identifying 20 fish species from 13,232 underwater images on coral reefs. The overall rate of species misclassification decreased from 22% with the raw DLAs to 2.98% after post-processing using the thresholds defined to minimize the risk of misclassification. This new framework has the potential to unclog the bottleneck of information extraction from massive digital data while ensuring a high level of accuracy in biodiversity assessment.

Predicting Microhabitat Suitability for an Endangered Small Mammal Using Sentinel-2 Data

Accurate mapping is a main challenge for endangered small-sized terrestrial species. Freely available spatio-temporal data at high resolution from multispectral satellite offer excellent opportunities for improving predictive distribution models of such species based on fine-scale habitat features, thus making it easier to achieve comprehensive biodiversity conservation goals. However, there are still few examples showing the utility of remote-sensing-based products in mapping microhabitat suitability for small species of conservation concern. Here, we address this issue using Sentinel-2 sensor-derived habitat variables, used in combination with more commonly used explanatory variables (e.g., topography), to predict the distribution of the endangered Cabrera vole (Microtus cabrerae) in agrosilvopastorial systems. Based on vole surveys conducted in two different seasons over a ~176,000 ha landscape in Southern Portugal, we assessed the significance of each predictor in explaining Cabrera vole occurrence using the Boruta algorithm, a novel Random forest variant for dealing with high dimensionality of explanatory variables. Overall, results showed a strong contribution of Sentinel-2-derived variables for predicting microhabitat suitability of Cabrera voles. In particular, we found that photosynthetic activity (NDI45), specific spectral signal (SWIR1), and landscape heterogeneity (Rao’s Q) were good proxies of Cabrera voles’ microhabitat, mostly during temporally greener and wetter conditions. In addition to remote-sensing-based variables, the presence of road verges was also an important driver of voles’ distribution, highlighting their potential role as refuges and/or corridors. Overall, our study supports the use of remote-sensing data to predict microhabitat suitability for endangered small-sized species in marginal areas that potentially hold most of the biodiversity found in human-dominated landscapes. We believe our approach can be widely applied to other species, for which detailed habitat mapping over large spatial extents is difficult to obtain using traditional descriptors. This would certainly contribute to improving conservation planning, thereby contributing to global conservation efforts in landscapes that are managed for multiple purposes.

Internet of Things to network smart devices for ecosystem monitoring

Smart, real-time, low-cost, and distributed ecosystem monitoring is essential for understanding and managing rapidly changing ecosystems. However, new techniques in the big data era have rarely been introduced into operational ecosystem monitoring, particularly for fragile ecosystems in remote areas. We introduce the Internet of Things (IoT) techniques to establish a prototype ecosystem monitoring system by developing innovative smart devices and using IoT technologies for ecosystem monitoring in isolated environments. The developed smart devices include four categories: large-scale and nonintrusive instruments to measure evapotranspiration and soil moisture, in situ observing systems for CO₂ and δ¹³C associated with soil respiration, portable and distributed devices for monitoring vegetation variables, and Bi-CMOS cameras and pressure trigger sensors for terrestrial vertebrate monitoring. These new devices outperform conventional devices and are connected to each other via wireless communication networks. The breakthroughs in the ecosystem monitoring IoT include new data loggers and long-distance wireless sensor network technology that supports the rapid transmission of data from devices to wireless networks. The applicability of this ecosystem monitoring IoT is verified in three fragile ecosystems, including a karst rocky desertification area, the National Park for Amur Tigers, and the oasis-desert ecotone in China. By integrating these devices and technologies with an ecosystem monitoring information system, a seamless data acquisition, transmission, processing, and application IoT is created. The establishment of this ecosystem monitoring IoT will serve as a new paradigm for ecosystem monitoring and therefore provide a platform for ecosystem management and decision making in the era of big data.

SPIKEPIPE: A metagenomic pipeline for the accurate quantification of eukaryotic species occurrences and intraspecific abundance change using DNA barcodes or mitogenomes

The accurate quantification of eukaryotic species abundances from bulk samples remains a key challenge for community ecology and environmental biomonitoring. We resolve this challenge by combining shotgun sequencing, mapping to reference DNA barcodes or to mitogenomes, and three correction factors: (a) a percent-coverage threshold to filter out false positives, (b) an internal-standard DNA spike-in to correct for stochasticity during sequencing, and (c) technical replicates to correct for stochasticity across sequencing runs. The SPIKEPIPE pipeline achieves a strikingly high accuracy of intraspecific abundance estimates (in terms of DNA mass) from samples of known composition (mapping to barcodes R²  = .93, mitogenomes R²  = .95) and a high repeatability across environmental-sample replicates (barcodes R²  = .94, mitogenomes R²  = .93). As proof of concept, we sequence arthropod samples from the High Arctic, systematically collected over 17 years, detecting changes in species richness, species-specific abundances, and phenology. SPIKEPIPE provides cost-efficient and reliable quantification of eukaryotic communities.

Biodiversity monitoring, earth observations and the ecology of scale

Human activity and land-use change are dramatically altering the sizes, geographical distributions and functioning of biological populations worldwide, with tremendous consequences for human well-being. Yet our ability to measure, monitor and forecast biodiversity change - crucial to addressing it - remains limited. Biodiversity monitoring systems are being developed to improve this capacity by deriving metrics of change from an array of in situ data (e.g. field plots or species occurrence records) and Earth observations (EO; e.g. satellite or airborne imagery). However, there are few ecologically based frameworks for integrating these data into meaningful metrics of biodiversity change. Here, I describe how concepts of pattern and scale in ecology could be used to design such a framework. I review three core topics: the role of scale in measuring and modelling biodiversity patterns with EO, scale-dependent challenges linking in situ and EO data and opportunities to apply concepts of pattern and scale to EO to improve biodiversity mapping. From this analysis emerges an actionable approach for measuring, monitoring and forecasting biodiversity change, highlighting key opportunities to establish EO as the backbone of global-scale, science-driven conservation.