Ecological Informatics

Artificial intelligence (AI)-based image analysis can efficiently estimate fish length, but differences in devices, imaging conditions, operators, and AI models limit comparability among surveys. We propose a standardization framework that estimates a bin-specific error matrix from paired reference measurements and AI-derived lengths and applies it to standardize (correct) AI-derived length-frequency distributions. The Richardson-Lucy expectation-maximization algorithm was used, with the number of iterations selected via cross-validation. Simulations based on empirical length-frequency data from 110 species showed that standardization reduced relative bias and distributional discrepancy; median relative-bias and root mean square error ratios were below 1, and the performance was more affected by the amount of paired data than by the number of cross-validation folds. In real data from 957 Japanese jack mackerel, standardized AI-derived distributions approached human-observer histograms, although discrepancies remained in the range of 160-230 mm. The proposed framework provides a practical approach for improving the comparability of image-derived length-frequency data using paired calibration data, without retraining the underlying AI model.

Camera trap networks such as Snapshot Safari have generated millions of labelled wildlife images across Africa, enabling the training of deep learning models for automated species classification. However, deploying models trained in one African region to another remains poorly understood. To the best of our knowledge, this study presents the first systematic evaluation of geographic domain shift within the African continent for wildlife camera trap species classification, using the Machine Learning sub-field of Artificial Intelligence. We use three model architectures, each interacting with Snapshot Serengeti in a different way: BEiTV2is fine-tuned on Serengeti images as a supervised baseline; DINOv2 with FAISS uses Serengeti images as a retrieval index without any weight updates; and BioCLIP is a true zero-shot foundation model that receives no Serengeti training data at all. All three are then evaluated on two Southern African test sets, Snapshot Kgalagadi and Snapshot Kruger, as well as on locally collected wildlife photographs from Botswana. We conduct eight experiments covering in-domain baselines, cross-dataset transfer, data scaling, MegaDetector preprocessing, grayscale vs. colour image conditions, and per-species transfer analysis. This work provides the first empirical characterisation of intra-African domain shift across both supervised and zero-shot architectures, and offers practical guidance for conservation AI practitioners who need to deploy models across the diverse ecosystems of Southern Africa without collecting new labelled data.

O_LIMonitoring and limiting the spread of invasive species on islands requires efficient detection and population estimation methods. However, elusive species can be difficult to monitor using traditional methods, making autonomous approaches such as camera trapping and acoustic monitoring increasingly valuable. C_LIO_LIOn the island of Okinawa, Japan, the small Indian mongoose ( Urva auropunctata) threatens many native species since its introduction in 1910. Listed among the worlds worst invasive species, effective monitoring of U. auropunctata in Okinawa is critical. The Okinawa Environmental Observation Network (OKEON) uses camera traps to detect U. auropunctata, but success depends on precise placement. Though OKEON also includes a high-resolution acoustic monitoring programme, no audio classification model currently exists for U. auropunctata. Developing such a model could improve substantially our capacity to detect and manage the species. C_LIO_LIUsing sparse U. auropunctata vocalisations collected from camera trap videos, we built a lightweight Convolutional Neural Network distilled from a more complex model for classifying contact calls and alarm calls of U. auropunctata. Our distilled model performed similarly to the full model at detecting vocalisations from training data, but was considerably faster. C_LIO_LIWe applied the distilled classifier to [~]486 hrs of audio collected over eight years from southern Okinawa, where we successfully detected U. auropunctata a handful of times in each year of recording. In spite of strong model performance on test data, our model did not transfer well to unseen data, perhaps owing to the rarity of U. auropunctata calls and consequent small training dataset size, limiting its utility for ecological monitoring. C_LIO_LIPractical implication. The use of sparse audio data from camera trap videos to train an acoustic classifier had limited utility to detect the rarely vocalising U. auropunctata from passive acoustic monitoring data. We provide several recommendations for enhancing classifier performance to provide robust actionable insights into the distribution and spread of U. auropunctata, and aid targeted conservation efforts for Okinawas threatened biodiversity. C_LI

Freshwater monitoring programmes like the European Unions Water Framework Directive (WFD) provide a wealth of data on European lake status, including water quality and macrophytes (aquatic plants) as critical habitat features that support health of humans and wildlife. Easier WFD data access can enable external management and research to better safeguard human and natural freshwater use. We demonstrate a replicable workflow to easily download and process multi-year (2007-2024) observations of lake macrophytes (425 sites) and complementary water quality variables (202 sites) from Swedish WFD data. Then, we illustrate the value of improved data access to address ecological questions that drive conservation, investigating how spatial scales influence macrophyte richness and associated water quality relationships using a spatial random intercept model. Decomposing the spatial intercept links small scales (<10 km) to site-level gradients and large scales (>100 km) to biogeographical drivers. Stochastic and environmentally-structured processes coexisted at intermediate scales (10-100 km). Adding water quality rarely improved overall predictive performance of macrophyte diversity models but consistently influences the role of different spatial scales. Water quality variables showed consistent spatially structured variation at intermediate scales and unique spatial patterns in tandem, overlapping with large-scale biogeographical influences. Altogether, we show context-dependencies for spatial model interpretation and provide guidance in accounting for spatial confounding to improve inferential and predictive performance. Our workflow and results show a clear way forward for accessing high-quality macrophyte and water quality data sets and their utility for addressing ecological questions that guide macrophyte protection under the WFD. HighlightsO_LIyears Swedish of macrophyte and water quality monitoring data were extracted. C_LIO_LIrichness showed scale-specific patterns linked to geographic gradients. C_LIO_LIbest predictive models for richness had no water quality at all. C_LIO_LIoverlap in their spatial scales and must be carefully separated. C_LIO_LIpen access data and multiscale analysis can apply to many ecological questions. C_LI

Automated monitoring of insect pollinators in natural environments with insect camera traps and trained deep learning algorithms provides novel data for insect ecological studies. However, efficient and accurate image recognition analysis of the recorded images or videos is challenging, particularly for images containing small insects against complex backgrounds with diverse vegetation communities. Even when insects can be detected in images, identifying their taxonomy remains difficult, particularly in footage with low image resolution, light conditions, and distances from the plants, and in cases where insects appear blurry or only partially visible. In this work, we present InsectDCT, an AI-based pipeline for automated detection, hierarchical classification, and tracking of insects in footage of natural vegetation tested in different environments. The InsectDCT pipeline consists of three levels: insect Detection and localization, hierarchical taxonomic Classification, and spatio-temporal Tracking. In the first stage, insects are detected in time-lapse images or video recordings using the You Only Look Once (YOLO11) object detection architecture. Detection performance is improved using motion-enhanced images, which improve robustness in cluttered and 3 dimensional environments. The detector is trained on an extensive dataset that contains more than 60,000 images collected using camera traps deployed across a wide range of plant families and floral habitats. In the second stage, detected insects are classified using a hierarchical taxonomy-aware classification framework that covers 80 taxonomic groups. Classification is performed at multiple taxonomic levels, including order, family, and genus/species, allowing coarse and fine-grained ecological analyzes while accounting for varying levels of visual ambiguity. In the third stage, a multi-object tracking module is applied to high temporal-resolution image sequences and video data to associate detections of the same individual across time. InsectDCT code and all datasets are made publicly available. Author summaryInsects are declining worldwide, creating an urgent need for efficient methods to monitor their abundance, activity, and diversity. Traditional insect surveys often require extensive fieldwork and expert taxonomic identification, which limits the scale and frequency of monitoring. In this study, we developed InsectDCT, an artificial intelligence-based pipeline that automatically detects, classifies, and tracks insects in camera-trap recordings collected from natural and semi-natural environments. Our approach combines deep-learning methods for object detection, hierarchical taxonomic classification, and tracking of individual insect observations through time. Unlike many existing systems that are trained for a single habitat or plant species, we designed our framework using images collected across a wide range of flowering plants, camera systems, and insect groups. This makes the system more transferable to new ecological settings. The classifier can identify insects at multiple taxonomic levels and can return higher-level classifications when species-level identification is uncertain. We demonstrate that the pipeline can process large image datasets efficiently, including on low-power edge-computing devices such as Raspberry Pi systems. By providing both the software and the underlying datasets, we aim to support scalable, non-invasive insect monitoring and facilitate future ecological and conservation research.

Antarctic benthic organisms are highly diverse and play a critical role in the Southern Ocean ecosystem. Despite decades of sampling, vast areas of the Antarctic continental shelf remain biologically unsurveyed due to logistical and financial constraints, limiting baseline knowledge essential for effective conservation planning. Species distribution models (SDMs) allow biodiversity to be inferred in the absence of biological data by linking benthic community patterns to environmental predictors. However, the resolution of the environmental predictors, particularly bathymetry, varies significantly between regions, casting doubt about how reliably SDMs can be used to predict into regions where only coarse-resolution data are available. Here, we show that SDMs trained on high-resolution data underestimate Antarctic benthic morphospecies richness by up to 18% when applied to aggregated coarse-resolution environmental data (and up to 50% when using satellite-derived ETOPO bathymetry). Using six systematically degraded versions of high-resolution multibeam bathymetry and annotated seafloor imagery across three Antarctic regions, we evaluate SDM performance both with and without additional environmental variables. High-resolution bathymetry captures terrain complexity most effectively, but we find that the spatial distribution of richness hotspots and the median richness per cell remain consistent, provided models are applied at the same resolution at which they were trained. Our results suggest that while high-resolution bathymetry may enhance local predictions, coarse-resolution data may be more robust for regional-scale predictions, such as those used for Antarctic shelf-wide spatial planning.

Habitat degradation and biodiversity loss in the Black and Azov Seas necessitate improved tools for spatially explicit conservation planning. We employed stacked species distribution modelling (SSDM) to assess habitat quality for the three resident cetacean species, the common dolphin (Delphinus delphis ponticus), the bottlenose dolphin (Tursiops truncatus ponticus), and the harbour porpoise (Phocoena phocoena relicta), which serve as apex predators and indicators of ecosystem health. Occurrence data were compiled from the Global Biodiversity Information Facility (GBIF), and ensemble species distribution models (ESDMs) were constructed using nine algorithms within the SSDM framework, with eight environmental predictors extracted from Bio-ORACLE v3.0. Individual ESDMs demonstrated excellent predictive performance (AUC: from 0.82 to 0.83; TSS: from 0.65 to 0.67; prop.correct: from 0.82 to 0.83). However, the initial continuous stacking method (pSSDM) yielded low community-level prediction success (0.36), prompting evaluation of three correction approaches. The Probability Ranking Rule (PRR) substantially improved performance (prediction.success = 0.459, sensitivity = 0.704, Jaccard = 0.465), effectively mitigating the overprediction bias inherent in stacked models. Species richness mapping identified multi-species hotspots along the southwestern Black Sea shelf, the Crimean coast, the Kerch Strait, and parts of the eastern coast, while the deep central basin exhibited the lowest richness. Variable importance ranking revealed bathymetry as the primary community-level driver (41.2%), followed by dissolved oxygen (13.8%), sea surface temperature (11.9%), and salinity (10.4%). Species-specific importance patterns confirmed ecological niche segregation, with common dolphins favouring deeper offshore waters and bottlenose dolphins and harbour porpoises associated with shallower shelf environments. The moderate richness observed in the highly productive northwestern shelf, despite high nutrient inputs, may reflect a combination of natural factors (elevated turbidity, reduced salinity) and anthropogenic pressures (fisheries bycatch, shipping, coastal development, and military activity) that limit species co-occurrence. Our findings demonstrate that PRR-corrected SSDM provides a robust framework for mapping cetacean habitat quality and identifying conservation priorities in the Black and Azov Seas, offering an evidence-based tool to inform ecosystem-based management in this ecologically unique and increasingly pressured marine region.

Circuit theory has been successfully applied to ecological connectivity modelling, notably via the Circuitscape software, which is typically run locally on a laptop or via a server. For downstream geospatial web applications relying on connectivity analysis, backend infrastructure is required, which can be costly and require advanced data governance. Recent developments in WebAssembly now allow fast C++ or Rust code to be run directly in a sandboxed browser environment for edge computing. We present a WebAssembly/Rust toolset with a geospatial data pipeline and efficient edge-computing implementation of connectivity analysis. This approach may be useful for geospatial modelling software where rasters and memory footprint are small enough for the browser context. Our results show that as expected, Circuitscape solves 1000x1000 raster networks 1-2x faster, but requires further file writes. Accounting for total program runtime, our web implementation can be faster for the given context.

Waterbirds serve as important indicators of both aquatic and terrestrial ecosystem health, making effective monitoring essential for tracking population health and identifying potential causes of decline. Drones have provided opportunities to overcome historic waterbird monitoring challenges, but the expertise and time required for manual image analysis creates a major bottleneck. Recent advances in deep learning-based object detection have enabled rapid, automatic detection of features in complex ecological imagery, though applications have largely been limited to single-species colonies, and practitioners lack quantitative comparisons of annotation time and accuracy across different levels of automation. We systematically compared four waterbird monitoring approaches using identical survey areas from Chester Island, a mixed-species colony in Matagorda Bay, Texas, in 2025: (1) traditional ground-based counts, (2) manual drone imagery-based counts, (3) computer-assisted counts using pre-annotations from an object detector with manual human verification (Human+ML), and (4) fully automated counts using object detector annotations (ML-only). We trained a YOLOv10 object detection model on manually annotated imagery of Chester Island in 2021 and applied it to the 2025 imagery. Manual drone annotation detected 6,530 birds in 40.5 hr and served as the primary reference standard. Human+ML detected 5,826 birds (89% of manual) in 7.7 hr, an 81% reduction in annotation time. ML-only detected 5,679 birds (87% of manual) in approximately 46 min, a 98% reduction. Ground counts recorded 5,868 birds (90% of manual). Detection generalized well across species while classification depended heavily on training data and morphological distinctiveness. The Human+ML workflow emerged as a practical middle ground, providing practitioners with empirical data to evaluate partial versus full automation strategies based on monitoring objectives.

Flower-visiting insect populations are declining since the 1990s, especially because of the decrease of floral resources in agricultural settings. Mass flowering crops can help increase resource availability, and plant breeding can be directed towards selecting varieties attracting more flower-visiting insects. This requires the implementation of an automated high-throughput phenotyping tool for assessing the attractiveness of plant genotypes to flower-visiting insects. In this study, (i) we present a procedure to take standardized images of sunflower heads with camera traps continuously at day and night in the field; (ii) we trained two versions of a deep learning model, named PolliCrop, to automatically detect and identify three classes of the main insects visiting sunflower on these images (non-Bombus bees, bumble bees, lepidopterans); (iii) we assessed and validated the ability of PolliCrop to correctly predict the true visitation frequencies of the insect classes on three sunflower genotypes; (iv) we presented two statistical approaches to compare the insect visitation frequencies between plant genotypes, one including weather variables, and the other one without. One PolliCrop version yielded satisfying performance to correctly detect the three insect classes. In particular, it correctly predicted the insect visitation frequencies on two sunflower genotypes in a range of {+/-}10%. The other PolliCrop version can be useful in certain contexts of images and objectives. PolliCrop can be extended in the future to other crop species by training PolliCrop on new images captured in these crops. The field experimental design to set up for comparing the attractiveness between genotypes is also discussed.

Premise: Rapid and accurate plant species identification is a critical challenge exacerbated by the taxonomic impediment. Although portable near-infrared (Micro NIR) spectroscopy represents a promising solution, the current absence of standardized protocols and a fundamental understanding of how critical acquisition and analysis parameters influence accuracy remain significant barriers. This study focused on the systematic optimization and validation of a comprehensive workflow designed to maximize the reliability of plant identification using this technology. To ensure methodological robustness across diverse foliar matrices, four vascular plant species were strategically selected as a representative test set to encompass morphological extremes, including significant variations in leaf thickness, pubescence, and surface texture. Methods: Using a portable spectrometer on herbarium specimens (exsiccate) of four vascular plant species, we systematically tested five spectral backgrounds, seven pre-processing methods, and four classification models. Subsequently, we optimized the number of spectral readings and evaluated the influence of the leaf scanning surface (adaxial vs. abaxial) on model accuracy. Results: The highest-performing combination was a Shiny Aluminum background, Second Derivative pre-processing, and a Random Forest model, which achieved a mean cross-validated accuracy of 99%. An average of just three spectral readings from the adaxial (upper) leaf face was sufficient to saturate model performance, proving statistically superior to other approaches (p < 0.001). Discussion: This study establishes a validated, high-accuracy protocol for plant species identification from herbarium specimens using portable NIR, offering a powerful tool for biodiversity studies. Direct applicability to fresh plants in the field requires future validation to account for the spectral influence of moisture variability.

Scientific bottom-trawl surveys provide essential fisheries-independent data for fisheries and ecosystem research. In the Northeast Atlantic, the ICES Database of Trawl Surveys (DATRAS) compiles haul-level information, species- and length-specific catch data, and individual biological observations across multiple long-term surveys. However, reproducible workflows for processing and integrating these relational datasets remain challenging. We present DATRASextra, an open-source R package that provides modular end-to-end workflows for accessing, cleaning, harmonising, quality-controlling, and analysing DATRAS survey data. The package supports derivation of standardised haul-level survey variables, integration of multiple surveys, and generation of analysis-ready datasets for downstream applications including stock assessment, biodiversity analyses, and large-scale synthesis efforts such as FishGlob.

Guava cultivation is considerably influenced by foliar and fruit diseases whose overlapping symptoms and environmental variability make accurate field-level diagnosis challenging. Numerous studies have been conducted to find efficient methods of diagnosing plant diseases, but most focus on image-level classification and do not include lesion localization or pixel-level segmentation of the images within a single framework of analysis. This study proposes a comprehensive framework for utilizing automated image analysis to classify guava leaf and fruit diseases at the image level, locate lesions, and segment lesions at the pixel level from multiple images of the same type of disease collected from various growing conditions. The dataset was enriched through three augmentation strategies including standard preprocessing, structured augmentation, and GAN-based synthetic image generation, expanding the effective training data to approximately 7,000 images, while a 5-fold cross-validation strategy guided model selection and final performance was assessed on a held-out test set. The experimental evaluation of multiple state-of-the-art Convolutional Neural Networks (CNNs) for the classification of guava leaf and fruit diseases indicated that the model generated using the ResNet50+DenseNet121 model fusion achieved the highest classification accuracy of 98.20%. For lesion detection and segmentation, YOLOv8-seg outperformed Mask R-CNN, achieving mAP@0.5 of 0.907 and 0.889, and mAP@0.5:0.95 of 0.783 and 0.769 for detection and segmentation, respectively, with a balanced precision-recall profile. The techniques of Explainable AI (XAI) were used to increase the transparency of this model by identifying areas in the image that are significant to the actual lesion. The framework was further designed with practical web-based deployment in mind, evaluating both lightweight and high-capacity models to balance computational efficiency against predictive accuracy. From this research, it was concluded that using model fusion, data augmentation, and segmentation-aware lesion detection would provide a solution for managing guava diseases effectively.

The Southern Hemisphere is home to extensive forests of giant kelp (Macrocystis pyrifera), including in Argentina and the southern islands of Tierra del Fuego, which has been proposed as a potential climate refugium. This study presents the first regional time series of M. pyrifera canopy dynamics in Argentina using Landsat satellite imagery from 1985 to 2023. The forests analyzed support 247.61 km{superscript 2} of emergent canopy and are situated in the coastal waters of Argentina and a small portion of Chilean islands, with 4%, 28%, and 68% in the Chubut, Santa Cruz, and Tierra del Fuego A.e.I.A.S, respectively. The small portion of Chilean Islands are included as part of the Tierra del Fuego province analyses. Range limits were scrutinized, in part, using expert knowledge and multisatellite comparisons. Linear regression shows that between 1998 and 2023, 7.4% of kelp sites exhibited a significant trend in annual canopy area, with all observed significant trends in the positive direction. Partitioning by province boundaries, linear regression produces significant positive increases in kelp canopy area across all three provinces, although reassessment when longer temporal continuity is also warranted, where available. Observed seawater nitrate concentrations were high throughout the region (7-23 {micro}mol L-{superscript 1}), suggesting that nitrate availability was not a primary driver of canopy variability. However, positive relationships between kelp canopy and the Antarctic Oscillation suggest that regional climate variability--which alters sea surface temperature and other oceanographic conditions--may be exerting a strong influence on kelp dynamics in this region. These findings document relative stability of kelp forest area in Argentina over the most recent two and a half decades and provide preliminary evidence supporting possible increases in kelp area for the region.

Elephants and other large mammals produce low-frequency vocalizations extending well below the 20 Hz lower limit of human hearing, a regime known as infrasound. These rumbles serve vital social and reproductive functions over distances of several kilometers, yet they are inaudible to human observers and cannot be reproduced by conventional small loudspeakers. We present a complete signal-processing pipeline that renders sub-20 Hz elephant rumbles perceptible through a small loudspeaker by exploiting the missing-fundamental psychoacoustic effect. Butterworth bandpass filters isolate the infrasonic content; a full-wave integrator nonlinear device (NLD) generates the harmonic series required for virtual pitch perception; and a hysteresis-comparator fundamental-frequency estimator normalizes the NLD output. The pipeline was validated on African elephant field recordings and deployed on a credit-card-sized, low-cost single-board computer with an infrasound microphone and a small Bluetooth loudspeaker, demonstrating live operation in the field. The processed output shows a 10 dB to 15 dB elevation in the loudspeakers efficient band during call segments compared with background. The system enables zoo visitors and wildlife observers to perceive elephant rumbles in real time, opening new avenues for behavioral studies and public engagement with animal communication.

Mosquito-borne diseases represent an escalating global health threat, driven by climate change, urbanization, and the spread of invasive vectors into new territories. Effective surveillance is constrained by a critical taxonomic impediment: the rate of specimen collection far outpaces the capacity of expert entomologists to process and identify trap catches. To address this bottleneck we developed MosAICo, an integrated AI-powered ecosystem for automated mosquito species identification designed for real-world, national-scale entomological surveillance. The system combines a standardized benchtop imaging device with MosAICo-Net, a deep learning pipeline enabling efficient and principled open-set recognition and uncertainty quantification. Trained and evaluated on 12, 499 specimens spanning 15 species collected across Italy, the model identifies seven priority vector species while explicitly rejecting out-of-distribution specimens. On a geographically stratified held-out test set, MosAICo-Net achieved over 90% accuracy on target species, and an AUROC of 0.96 for out-of-distribution detection. Field validation across 20 Italian surveillance sites confirmed these results: 94% micro accuracy on 1, 470 field-collected target specimens and strong agreement with expert manual counts ([Formula] = 0.66). To assess cross-geographic generalizability, the system was further evaluated on 118 Aedes albopictus specimens collected at the fringe of the species invasion front in Ghana: a 97.4% accuracy with only a single specimen escalated to expert review, suggests that MosAICo is well-suited for deployment in distant and epidemiologically critical regions. The system processes up to 82 specimens per image, matching expert throughput at constant speed regardless of taxonomic complexity. By embedding uncertainty-aware AI within a standardized hardware-software pipeline, MosAICo acts as a scalable force multiplier for public health entomology, freeing expert attention for rare, invasive, or ambiguous specimens that require human validation.

Species distribution models (SDMs) increasingly inform conservation and biosecurity decisions in freshwater systems, where the reliability of its uncertainty estimates matters as much as its point predictions. Ensemble SDMs derive prediction intervals from across-replicate variance, but this variance captures systematic error only when replicates disagree about it, an assumption that fails when training data are contaminated with low-accuracy records, the norm in citizen-science datasets. Whether this failure is spatially uniform or concentrates in identifiable parts of a range is unknown. Using a panel of European freshwater crayfish spanning native headwater-associated species and invasive lowland colonizers, we show that contamination-induced calibration failure is strongly spatially structured: it concentrates at stream-network headwaters, the topological tops of the network, where upstream-aggregated predictors are structurally undefined, and scales with contamination severity, replicated across four species and both dominant ensemble protocols (replicate and consensus). The failure is driven by upward prediction bias, not by intervals failing to widen: contaminated ensembles overpredict suitability in headwaters, and because the bias is shared across ensemble members, the intervals do not flag it. This is a conservation-relevant blind spot, because headwaters are both refugia for threatened native crayfish and front lines for invasion; an SDM that silently overpredicts suitability there misdirects survey and management effort toward the segments where its predictions are least trustworthy. Standard leave-one-basin-out conformal calibration, the recommended panel-wide remedy, repairs marginal coverage but leaves headwaters undercovered, because a single calibration threshold is dominated by the abundant non-headwater segments. A group-conditional (Mondrian) variant, calibrating the two populations separately, restores reliable coverage in both at no extra cost and reallocates width where it is needed. We recommend network-position-stratified calibration as a default for ensemble SDMs in dendritic freshwater systems.

The advancement in deep learning techniques has made Convolutional Neural Networks (CNNs) a powerful tool for the fully automated classification of zooplankton images. In this study, we systematically investigate how network selection, colour information and differences in imaging instruments affect the classification of zooplankton images by comparing multiple state-of-the-art CNNs on images of zooplankton and marine snow from the in situ Continuous Particle Imaging and Classification Sensor (CPICS), Video Plankton Recorder (VPR), In Situ Ichtyoplankton Imaging System (ISIIS), and the on-board Plankton Imager (Pi-10). With differences between models of 7.8 to 19% in F1-score, we find that model selection strongly affects the classification performance, with EfficientNetV2S showing the most reliable overall performance. Moreover, differences between model architectures are largest for the least abundant classes (<100 labeled images), which implies that when these are present, careful model selection is most beneficial. The high image quality of the Pi-10 strongly increases the performance for the least abundant classes compared to the other instruments. In addition, we find a significant correlation (r = 0.597) between ImageNet the performance and F1-score on zooplankton images, which implies that more generally, a model that performs well on ImageNet will perform well for zooplankton classification. Colour information increases the F1-score of the best performing classifier with 2.8%, but provides a stronger benefit (25% F1-score) for classes with <100 images. The overall performance increase of colour information is less than expected and questions the advantage of recording colour information for zooplankton.

Protected areas cannot halt biodiversity loss in isolation; integrating them with surrounding human-dominated landscapes is critical. However, this integration is challenged by substantial landscape heterogeneity at their borders, hindering our understanding of cross-border changes in ecosystem service provision. We introduce a novel framework for characterizing these dynamics by analyzing ecosystem service gradients along protected area borders. For 16 protected areas in the French Alps, we assessed 12 ecosystem services using a mix of established biophysical models and novel connectivity-based models for mobile species. These were aggregated into three stakeholder-driven domains reflecting respectively rural, cultural, and urban management priorities. Automated polynomial regression analysis classified borders into five gradient types. The most common were 'Decreasing Gradients', representing a decline in ecosystem services outside the protected area, and 'Increasing Gradients', with the opposite pattern. Our analysis reveals these patterns are driven by specific landscape configurations, uncovering frequent trade-offs between the three management priorities, where, for instance, landscapes supporting rural priorities often degrade cultural and urban ones. We also identify key opportunities for synergies, by identifying areas where ecosystem services for all three priority domains increase simultaneously outside the protected area. This spatially explicit typology provides a powerful diagnostic tool for designing targeted interventions, such as prioritizing habitat restoration where ecosystem services decline or managing agricultural landscapes to mitigate conflicts across management priorities, supporting a more effective integration of protected areas into the wider landscape.

Knowledge regarding variation in habitat use among individuals is crucial for understanding population dynamics and for management and conservation measures. This is especially important for diadromous fishes that shift between habitats, being affected by external pressures and environmental change in different habitats over ontogeny. Herer, we assessed individual variation in habitat use of European eel along a salinity gradient, ranging from fully marine to freshwater in northern Europe, using otolith microchemistry data from >3600 eel together with established time-series segmentation and clustering methods. We show that eel display high degree of individual variation in habitat use. Assigned life-histories included coastal resident, freshwater resident, and coastal and freshwater habitat shifting individuals. Coastal resident eels were observed in a large range of salinities. Given the widespread occurrence of migration barriers in freshwater, it is unknown whether the coastal resident eel preferred that habitat, or if it was the only available habitat for them. Our findings nonetheless highlight the need to include coastal habitats when assessing population development and silver eel production of the critically endangered European eel.