Methods in Ecology and Evolution

Automated monitoring camera systems offer an efficient approach for quantifying pollinator biodiversity and plant-pollinator interactions, but financial and logistical constraints limit the number of flowering plant species that can be monitored. Using a large European database of plant-pollinator networks, we evaluated whether plant subsampling can capture key metrics of interest (i.e. pollinator richness and network structure). We compared abundance-based, flower-shape-informed, phylogenetically informed and random plant sampling. Abundance-based sampling consistently outperformed random sampling, while adding flower shape provided little additional benefit and phylogenetic selection performed similarly to random sampling. Overall, monitoring 12-15 flowering species was sufficient to characterize key network properties across varying community sizes. Performance of abundance-based plant sampling declined in species-rich communities and when rare but highly attractive plants were present in the community, while a specific subset of pollinator species was consistently missed even by the best sampling strategy. Based on their relative contribution to interactions within each network, only 12.6% of pollinator species accounted for 95% of interactions, suggesting that AI classifiers could prioritize a relatively small subset of species. Our results provide practical guidance for designing efficient camera-based pollinator monitoring schemes at large spatial scales.

1. For many animals, vision represents the primary sensory modality governing a vast diversity of behaviours. Creating 'virtual twins', or visually realistic digital reconstructions of real individuals interacting within their environments, offers a promising approach for understanding how visual information guides an animal's decisions, behaviours, and interactions. Such systems enable the creation of video scenes from any view, including the viewpoint of the animals themselves. This allows receiver information to then be analysed from the perspective of species-specific visual systems, or for the accurate reconstruction of a real animal's movement to provide social stimuli for behavioural experiments. 2. Despite advances in 3D modelling, photorealistic scene rendering, and animal tracking, efficiently creating realistic digital reconstructions of movement remains challenging for many species. In fishes, a continuously-deforming body due to the absence of discrete joints make it particularly difficult to map tracked body keypoints onto articulated digital models, often resulting in unnatural or erratic animations. 3. Here, we introduce DigiFish, an add-on for the open-source animating software Blender, that generates realistic fish animations from tracking data. By integrating anatomical keypoint tracking with spline-based body curvatures, DigiFish reconstructs biologically-realistic swimming postures and movements of fishes within customisable virtual aquatic environments. The system also supports virtual 'point-of-view' cameras that can be placed arbitrarily within a scene, or dynamically driven by eye-tracking data, enabling unlimited perspectives on how individuals, conspecifics, or landmarks appear against complex backgrounds and how these views change with realistic swimming and eye movements. 4. We provide the Blender add-on and user guide and use DigiFish to reconstruct two different contexts: staged predator-prey interactions in the laboratory and natural schooling of wild fish in the field. Using a further reconstruction of fish swimming in an arena, we also use an Elementary Motion Detector model to show that our virtual reconstructions successfully capture perceptually-realistic movements and postures of individual fish within a digitally reconstructed scene. 5. By integrating photo-realistic scenes with biologically-realistic, simulated motion, DigiFish offers a flexible and accessible platform for investigating visually guided behaviour, perception, and cognition in complex and dynamic environments.

Species distribution models are widely used for the evaluation and analysis of species spatial distributions and responses to environmental changes. Due to this, there's a wide diversity of tools and algorithms to perform these types of analyses. However, despite being a mature field of study, SDM still requires a large amount of research intervention and decision-making to produce reliable models. This is a natural consequence of each species unique response to environmental factors, but in practice it hinders the potential of SDMs to be used effectively and with confidence across large sets of species. Here we present the AutoMaxEnt repository, a collection of functions and tools for the automation of maximum entropy species distribution models. AutoMaxEnt offers a flexible environment to model species distribution models, automating most of the data pre-processing and preparation and giving the user the possibility of exploring multiple model scenarios automatically or with control over how those scenarios are generated. AutoMaxent offers model fit control, multiple background points generation algorithms, automatic model and variable selection, and study area configuration, among other parameters. AutoMaxEnt allows for the automation of model fitting, evaluation and model selection across different species, study areas and time periods.

1. Thermal performance curves (TPCs) are widely used to quantify temperature dependence of biological traits, but estimating them requires experiments across multiple temperatures. Because these experiments can be costly, researchers must balance the number and placement of temperature treatments against replication within treatments. Evenly spaced temperatures are a common default, but may allocate effort inefficiently when thermal responses are nonlinear or strongly asymmetric. 2. We developed TPCdesign, an R package for planning temperature-trait experiments. TPCdesign uses a pseudo-Bayesian (robust) D-optimal experimental design to identify sets of temperatures expected to provide the most information about a TPC, while allowing users to incorporate prior knowledge of thermal limits and curve shape, uncertainty in that knowledge, available numbers of treatments, and practical restrictions on temperature spacing. 3. Using simulation-based worked examples, we show that optimized designs can recover TPCs more accurately than evenly spaced designs, particularly for asymmetric curves and when the number of available temperature treatments is modest. Optimization primarily improves resolution of regions where performance changes rapidly and can substantially improve estimation of upper thermal limits while retaining information across the rest of the curve. 4. TPCdesign provides a practical framework for allocating limited experimental resources according to the biological response researchers seek to estimate. Rather than prescribing a universal set of temperatures, it allows experimental designs to reflect existing biological knowledge, uncertainty, and logistical constraints, improving the information gained from costly thermal performance experiments.

Ecoacoustic monitoring is enabling scientists and land managers to monitor and manage biodiversity more effectively and cost-efficiently in the face of human pressures and rapidly changing climates. Currently, most ecoacoustic surveys use manually deployed static sensors to record data, limiting the scale and reach of surveying efforts. Here we present a proof-of-concept autonomous drone platform that can use intermittent locomotion to conduct ecoacoustic surveys using an onboard sensor. Our custom prototype is able to fly, navigate, and avoid obstacles autonomously, land at a pre-determined location, record audio from an onboard microphone whilst static, before taking off and moving to the next sampling site. Autonomous navigation and operation enable greater sampling flexibility, reach, and scalability. Furthermore, by recording audio only whilst landed, noise from the drone's rotors does not mask signals or disturb animals, simplifying signal processing and downstream ecological analyses. We conducted trials in a scrubland habitat at the Knepp Estate in West Sussex, where our prototype demonstrated successful autonomous navigation and obstacle avoidance. Furthermore, we found that avian biodiversity data collected from the drone platform was comparable to that from traditional static acoustic sensor deployments, and that vocalisation patterns were not significantly impacted by the noise of the drone arriving or leaving a site. While scaled deployments of our technology would require further technical and regulatory challenges to be solved, our first demonstration of autonomous intermittent robotics-assisted ecoacoustic surveys lays the foundations for more cost-effective and far-reaching biodiversity surveys, with transformative potential for conservation, agricultural management, biosecurity, and more.

Protecting deep-sea sessile communities as Marine Protected Areas (MPAs) requires accurate estimates of their spatial distribution and abundance. Existing computer-vision detection methods require careful calibration to avoid counting errors; multi-object tracking (MOT) theoretically offers a more robust alternative. In practice, however, poor lighting and turbidity limit the efficacy of purely kinematic MOT algorithms in deep-sea environments. At the same time, the intra-species visual homogeneity typical of deep-sea scenes means traditional per-frame appearance features are often too weak to maintain stable identities in deep-association MOT algorithms. In this paper we introduce JEPA-SORT, an MOT algorithm that injects V-JEPA 2.1 embeddings into detection-to-track association, to show that video world-model embeddings - which capture not only physical appearance but spatiotemporal trajectory across viewpoints - can help maintain stable identities on visually homogeneous specimens. We provide a benchmark of twelve ROV transects surveying deep-sea sessile communities and evaluate JEPA-SORT against standard MOT algorithms across a range of simulated optical environments. We also propose the Biodensity Utility Metric (BDU), which measures tracker performance in the context of downstream ecological modeling. JEPA-SORT outperforms all benchmarked trackers on IDF1, MOTA, and BDU and is competitive on specimen-count accuracy. Ablations indicate its advantage stems primarily from the discriminative power of world-model embeddings on visually homogeneous footage.

1. Soil invertebrate biomass is closely linked to ecosystem processes, yet its routine quantification remains constrained by the effort required to weigh large numbers of small individuals. Length-mass relationships provide an indirect alternative, but body length can be difficult to standardise and extract automatically from images of curved, coiled or contracted organisms. Projected body area may provide a more tractable image-derived predictor, but its performance across diverse soil-faunal taxa and at the community scale remains insufficiently evaluated. 2. Here, we developed a framework using projected body area and contour length to estimate fresh and dry mass from measurements of 1,792 soil invertebrates representing 15 higher-level taxa. We fitted taxon-specific models for six well-represented groups and general models across taxa, and evaluated predictive performance using leave-one-out cross-validation. We then assessed cross-dataset transferability by comparing our data with those of Lemoine et al. (2026) and pooled the two datasets to derive combined models. Finally, we tested whether individual predictions could be scaled to independently measured community biomass. 3. Taxon-specific models generally reduced prediction error relative to general models, with mean absolute percentage error (MAPE) values of 6.9-37.3% for fresh mass and 7.6-30.2% for dry mass. General models retained MAPEs of 27.2% and 22.4%, respectively. Comparisons of our dataset with that of Lemoine et al. (2026) showed no detectable differences in six of eight taxon-by-mass slopes. Although intercepts frequently differed, no overall dataset effect was detected after accounting for taxa. Pooling both datasets broadened model development, while taxon-specific models generally retained lower error than the combined general model. Finally, community-level predictions tracked measured biomass across all model sets (R2 = 0.87-0.99), but absolute error varied among models and faunal groups (MAPE = 9.6-52.5%). 4. Body area and contour length extracted from images therefore provide a practical basis for scaling soil invertebrate biomass estimation from individuals to communities. Integration with automated imaging and segmentation tools such as flatbug, BIODISCOVER and CollembolAI could extend soil invertebrate monitoring at larger scales beyond abundance and taxonomic composition to biomass, while providing scalable inputs for analyses of food webs and general ecosystem ecology.

(1) Kelp forests support ecologically, commercially, and culturally important species, yet their benthic communities remain difficult to monitor consistently across space and time. Scientific SCUBA surveys provide valuable observations but can be constrained by safety, bottom time, depth, and the spatial extent that divers can efficiently cover, motivating complementary approaches for collecting standardized benthic imagery. (2) We developed and field-tested a standardized, open-source framework for benthic visual-imaging surveys using a small, modular remotely operated vehicle (ROV). Across four cost-scalable hardware configurations, we integrated navigation sensors, custom BlueOS Extensions, and our surftrak contribution to ArduSub, which enables fixed-altitude flight above the seafloor, and developed two open-source desktop applications that streamline field operations (rov_flight_ops) and imagery processing (rov_imagery_processing). We also evaluated power supplies, benthic lighting, camera settings, field protocols, and telemetry-processing workflows over 303 transects conducted on 64 survey days from 2022 to 2026. (3) The ROV operated across soft-sediment and rocky habitats, currents of 0-3 kt, and underwater visibility of 0-10 m. surftrak held the ROV within 0.2 m of its target altitude for 96% of 21 h of survey transects, producing an approximately 1 m^2 standardized image footprint. Sufficient illumination and optimized camera settings yielded high-resolution imagery in visibility below 2 m, while topside power increased endurance and operational flexibility. Combining Doppler velocity log and underwater acoustic positioning data through the vehicle's extended Kalman filter improved navigation and post hoc transect reconstruction. During 2026 surveys, rov_flight_ops and rov_imagery_processing automated flight logging, log retrieval, fault diagnosis, and the sorting, development, and telemetry annotation of survey imagery. Dense kelp canopies nevertheless constrained vehicle operation, and downward-facing imagery provided limited observations of cryptic or obscured organisms. (4) We provide configuration-specific bills of materials, hardware and wiring documentation, software and firmware inventories, camera settings, open-source field and imagery-processing software, step-by-step field protocols, and pre- and post-dive checklists to support replication and adaptation of the framework. Together, these resources provide a field-tested starting point for expanding standardized benthic imaging while complementing diver surveys across kelp forests and other shallow coastal ecosystems.

Motion-activated camera traps are an effective tool for monitoring animals, but a single study can produce millions of images, which must be analyzed before they yield data. The burden of analyzing them has led many teams to automate the work with computer vision. These models lose accuracy on images unlike those they were trained on, however, and a general model may not use the categories a project needs. Adapting a model to a project usually requires at least one of the following: many labeled images per species, programming expertise, a graphics processing unit (GPU), or uploading images to a remote server. I describe WildObserve, a desktop application that adapts to each project without any of these requirements. SpeciesNet suggests a species for each animal that MegaDetector finds, and WildObserve keeps SpeciesNet's feature vector for each one. A project model, a logistic regression on those features, then retrains in about a second as the reviewer labels, learning the project's own species and names. From the reviewed records, and optionally the suggestions, WildObserve also fits occupancy and abundance models. Images stay on the user's computer, and every record says which model suggested its species and who confirmed it. WildObserve processed 8.1 images/s on an Apple M1 Pro laptop. On Oregon Critters, a dataset released after SpeciesNet was trained, the project model's accuracy passed that of SpeciesNet with ten labels per species (balanced accuracy 0.783 against 0.751). I also tested occupancy on 63 cameras in Malawi that SpeciesNet had not seen. With 5% of the images reviewed and the project model's suggestions counted for the rest, species' occupancy estimates differed from those of a full review by 0.11 on average. From the reviewed images alone, they differed by 0.41. WildObserve takes a project from images to species records in its own categories and on to occupancy estimates, without writing code, needing a GPU, or sending images elsewhere.

Early detection of invasive species is critical to efficiently managing biological invasions. Passive acoustic monitoring combined with deep learning has become an effective tool for identifying invasive anurans from their species-specific mating calls. In practice, however, these systems still depend on manually retrieving recordings and running inference on a dedicated workstation, which delays detection at invasion fronts, especially on remote islands where frequent travel is impractical. Here, we present a lightweight convolutional neural network for detecting Rhinella marina and Polypedates leucomystax that can be used with low-power microcontrollers, enabling continuous, real-time monitoring of these invasive species. Our model achieved a mean invasive-species F1 of 0.87 with precision higher than 0.88 for both species, comparable to the performance of substantially larger models at a fraction of the model size. Cross-domain evaluation confirmed reliable detection on two out-of-training locations: Iriomote Island, Japan, and on an independent dataset from Australia, demonstrating generalization across recording conditions and biogeographic contexts, albeit with local threshold calibration for P. leucomystax at Iriomote. Our results demonstrate that effective acoustic detection of invasive species is feasible on self-contained, battery-powered devices, removing the dependence on server infrastructure and enabling autonomous early warning systems in remote protected areas.

Species delimitation increasingly relies on multiple sources of evidence, but most frameworks are still limited to genetics and morphology or analyze data types separately and compare results qualitatively. We present delimSOM 2.0, an R package that leverages unsupervised machine learning through multilayer self-organizing maps. Any kind of input data, including genomic, phenotypic, ecological, and spatial, is analyzed jointly, retaining each data type as a separate layer and balancing their contributions through layer-specific weighting. Our package provides functions for preprocessing, replicate training, multivariate clustering, hyperparameter optimization, model-quality assessment, and variable- and layer-importance analyses. We evaluated our approach using two simulation sets and eight empirical studies spanning diverse taxa and data types. Overall, performance was strongest with larger sample sizes (>10 individuals per lineage) and modest numbers of lineages (K < 5), but unlike most species delimitation methods, it can reliably infer K = 1. Across two-population demographic simulations of genetic data, our method performed similarly to the well-established DAPC across gene-flow and sampling regimes, was more conservative than STRUCTURE and sNMF in inferring K = 2 and showed mixed support for K = 1 and K = 2 at intermediate differentiation levels and with gene flow. Crucially, our method is robust to missing data and variation in hyperparameters. Empirical examples showed that genetic data were typically most influential, but phenotypic, ecological, and spatial layers often contributed substantial complementary information. By combining diverse data types into a single unsupervised analysis, delimSOM 2.0 enables fully integrative species delimitation, reduces over-splitting, and advances efforts toward more objective and standardized taxonomy and speciation biology.

Climate affects biological processes and organisms. It is extensively recorded, and its effects are frequently studied. Climatic variables are recorded as time series of measurements, but these are often summarized as long-term averages, throwing away biologically relevant information. Subsequent analyses can therefore miss important climate effects or suffer from low predictive power. Here, we propose a new method, StatClim, inferring the most informative climatic summary from the data. Instead of taking a fixed arbitrary summary of a time series, StatClim automatically estimates the beginning and width of a climatic window and simultaneously calculates data aggregation, which best predicts a response variable. We implemented the proposed approach as a Bayesian hierarchical model in Stan. We illustrated the potential of StatClim on published data on mast seeding of Fagus sylvatica. StatClim correctly identified known climatic windows relevant for this tree species, but also uncovered that mast seeding is triggered by high temperatures within these windows. We demonstrated flexibility of the model to account for complex data structures, we ran power analysis showing the ability of the model to identify climatic effects even with modest datasets, and we evaluated its false positive rate, which is lower than 0.01. We discuss the advantages and limitations of StatClim. Compared to existing alternatives, it is suitable for hypothesis testing and offers important advances, such as estimation of the type of aggregation. In combination with existing methods, StatClim will facilitate data-driven use of climatic and microclimatic data and therefore discovering so far unknown climatic effects on biological processes and ecosystem functioning.

Abstract 1. Biomes are continental-scale vegetation units widely used in ecological and evolutionary research, often together with large-scale species-distribution data. Many conceptually distinct biome schemes exist, differing in the underlying definition, delineation methodology and spatial resolution, yet most studies using biomes default to a few readily available schemes rather than choosing the one best suited to the research question. 2. We present biomes, an R package distributing spatially explicit raster layers of 31 published global biome schemes in a harmonised format at a 10 x 10 km resolution, together with metadata and a concise description. To facilitate their use, biomes provides a user-friendly classification workflow to classify occurrence records into specific biomes and a data-driven ranking algorithm to help researchers to choose the most suitable biome scheme for their data and research question in a transparent, reproducible way. 3. The biomes workflow can be applied to any dataset of georeferenced terrestrial occurrences. It (1) accepts either user-provided occurrence records or records downloaded by the package, (2) ranks the schemes according to their fit to the occurrence data, (3) assigns the records to specific biomes, and (4) summarises the resulting taxon-biome patterns. We demonstrate this workflow using 17,030 occurrence records of 185 species of Bombacoideae (Malvaceae). The analysis identified the vegetation-based biome scheme of Ramankutty and Foley (1999) as the best fit and recovered the forest and savanna biome signal known in the group from the literature, with tropical evergreen woodland being the biome with the largest share of records (46.1%) and highest number of species (162 of 185 species; 87.6%). 4. biomes provides user-friendly access to technically standardised and spatially explicit layers of 31 biome schemes, and thereby enables the transparent, data-driven choice of biome schemes tailored to a specific research data and questions, improving the reproducibility and the specificity of biome use across ecological and evolutionary research.

Recent work on the design of spatial capture-recapture (SCR) studies has largely focused on settings with a single set of movement and detection parameters. In many applied contexts, however, populations are naturally stratified-for example, when different sexes exhibit markedly different movement scales and encounter processes, or when more than one focal species is monitored. Designs that perform well for one group may be inefficient or suboptimal for others, despite the substantial logistical effort typically required to implement an SCR survey. We describe several potential SCR design strategies for surveying multiple groups, and compare these using simulation. Designs considered include regular and optimised grids, clustered and lacework designs, and designs generated using genetic algorithms, including new approaches that optimise information from both groups and a recently published two-stage design. Using proximity detectors such as camera traps, we evaluate design performance in terms of precision, bias, and coverage, and examine how performance changes with the number of available resources. Our results show that multi-group SCR surveys can perform well even when focal groups differ greatly in movement scale and encounter rate, provided that some simple guidelines are followed. Systematic layouts accommodating more than one characteristic spacing e.g. cluster designs, performed consistently well and are a reliable default option. Regular grid designs with a single spacing between detectors are feasible when differences between groups are moderate but performed poorly as differences increased. Establishing when these designs become problematic adds unnecessary risk to the design process. Algorithmic designs did not outperform systematic designs even in highly-skewed scenarios expected to favour them. In practice, when there is more than one focal group we recommend identifying the smallest and largest plausible movement scales and rejecting potentially pathological designs, primarily those that cannot generate recaptures at the smaller scale or cover a substantial area at the larger scale.

Habitat destruction leads to a severe decline in biodiversity. Ascertaining effects of habitat loss afterwards is regularly done, whereas predicting the effects of different habitat loss scenarios on biodiversity beforehand is much preferred but as of yet rarely possible. Such predictions would help inform management decisions to prevent biodiversity loss in the first place, or at least mitigate effects if necessary, by providing handles to set priorities in making trade-offs. To this end, we developed and applied an adapted version of the information-theoretical framework of Maximum Entropy Theory in Ecology (METE) to predict species-area relationships in tropical forest landscapes undergoing habitat loss and fragmentation. Species-area relationships provide information about biodiversity and can, in undisturbed systems, be predicted using METE, based on state variables such as the total number of individuals, the total number of species, and the total area size. In disturbed systems, however, it is established that METEs predictions are off. Using an individual-based model, we explore how METEs state variables should be adjusted, based on the landscape characteristics habitat cover and degree of habitat fragmentation, to restore its accuracy of species-area relationship predictions in disturbed environments. We validate our adjusted METE predictions with empirical data. Our adjusted METE predictions demonstrate the severity of fragmentations impact on biodiversity, relative to what could be expected in a pristine, continuous environment. With this new method, we can estimate the immediate effects of habitat loss on biodiversity, as well as its long-term effects.

Understanding the consequences of global change for our ecosystems requires reliable, accurate, and scalable tools for detecting ecological change. To this end, recent efforts have focused on scaling up the quantification of demographic processes from individual organisms (the fundamental ecological unit) to the larger spatial scales they inhabit to yield more precise and informative estimations of ecological change, especially in response to disturbance. Here, we describe a transferable workflow that combines robust underwater photogrammetry techniques with machine-learning-assisted image analysis to quantify demographic changes in coral colonies (growth, stasis, partial mortality, and complete mortality) through time on the reef landscape. We then demonstrate several analytical applications of this workflow that can be broadly applied to sessile and/or clonal organisms in other ecosystems. First, we tracked the fates of 3,162 coral colonies through a marine heatwave that caused substantial mortality. Second, our approach enabled detection of size- and taxon-dependent patterns in demographic changes from before to after the heatwave. Finally, for a subset (425) of these colonies, we further demonstrated how our method can be used to track fates across multiple years, including a year of change before and after the heatwave took place, revealing nuanced patterns of survival and mortality, as well as changes in size structure that occurred before and after the disturbance. Our workflow offers an important advance for increasing the accuracy of change detection on coral reefs and other ecosystems by linking demographic changes in individual organisms with spatially extensive image-based surveys through time.

Reliable demographic data are critical for seal population assessment and management, yet remain challenging to obtain from drone surveys without automated tools. Using data from harbor seal (Phoca vitulina) haulout surveys conducted in British Columbia, Canada, in 2023-2024, we developed and tested an automated pipeline that integrates detection, morphometric extraction, and size-class classification of seals into a single system. The pipeline combines cascaded DeepLabV3+ segmentation (water removal, colony-level seal detection, and individual body-contour refinement), principal component analysis (PCA)-based extraction of body length and maximum width, and three-class size-class determination based on body length (pups, juveniles, subadults/adults). We evaluated the pipeline on 2,483 manually annotated seals across four drone platforms (DJI Mavic 3 Thermal, Mavic 2 Pro, Mini 3 Pro and Mini 2), five substrate types, and two sensor modalities (RGB, thermal infrared). Aggregate detection F1 was 0.914. Orthomosaic geometric accuracy, quantified as the RMSE of calibration-rod length on the orthomosaic, ranged from 1.0 cm to 18.0 cm depending on the platform-altitude-substrate combination, a spread that aggregate metrics would mask. Relative to manual annotation on the same orthomosaics, automated RGB body lengths showed near-zero bias (-0.6 cm; RMSE = 12.5 cm), whereas automated thermal lengths were systematically shorter (bias -19.9 cm, RMSE = 24.1 cm), establishing the unsuitability of thermal imagery for automated quantitative pinniped morphometry. For RGB imagery, threshold classification by body length reached an overall accuracy (OA) of 78.7%; for individuals outside the uncertainty zones (defined as {+/-}2 x the geometric RMSE on calibration rods around each class boundary), OA reached 90.9%. Within the RGB subset, OA was 78.9% at 20 m altitude, declining to 75.0% at 40 m where geometric error dominated. The pipeline enables automated demographic monitoring of pinniped haulouts with quantitatively characterized uncertainty across survey conditions.

Data curation-the process of collecting, cleaning, and joining raw datasets for unified analysis-is a time-consuming yet crucial part of any data science project. With the emergence of powerful agentic coding tools, it is tempting to "vibe curate"-i.e., to prompt AI agents to perform data curation operations and blindly trust their outputs in order to finish work more quickly. However, this can exacerbate two key challenges that already plague manual data curation workflows: reproducibility-the ability to trace the exact set of modifications applied to raw datasets-and verifiability-the ability to audit changes and confirm that data is processed properly. To address these issues, we introduce Scrub Data, a framework that enables the use of AI agents in data curation workflows while transparently maintaining both reproducibility and verifiability. The framework involves an interactive data curation loop between a user and an AI agent, backed by a data provenance graph that tracks and versions all dataset updates. The data graph requires that all updates are formatted as self-contained executable steps, allowing any version of a dataset to be reconstructed from raw data by playing forward the transformations stored in the graph. This workflow takes place within a lightweight web application that is designed to be modified by users and agents in real-time to create custom visualization tools for identifying data curation needs and verifying outcomes. We demonstrate the usefulness of the framework with a real data curation use case from animal movement ecology. Starting with 89M raw GPS coordinates, we use the framework to curate a benchmark dataset of 2.5M coordinates to be used for machine learning or statistical analysis. The framework is available for use and extension at https://github.com/justinkay/scrubdata.

Understanding floral visitor dynamics along elevational gradients is essential for assessing potential implications for pollen limitation and population genetic processes in fragmented populations of cliff-dwelling alpine endemics. Physoplexis comosa (Campanulaceae) is a chasmophytic paleoendemic restricted to vertical rock faces on dolomitic and limestone bedrock from 200 to 2,800 m a.s.l. The species exhibits a specific floral morphology with fused corolla apices, basal openings for nectar access, and secondary pollen presentation, yet its functional floral visitor assemblage has remained poorly characterized across the species' elevational range. In this pilot study, we tested a two-tier camera-monitoring setup combining action cameras for diurnal monitoring with Raspberry Pi-based systems equipped with IR illumination for combined diurnal and nocturnal recording. We conducted monitoring across five elevational sites (1,480 to 2,400 m a.s.l.) in the Eastern Alps. Recorded video material was downsampled and annotated using the Addax platform alongside manual cross-validation to record physical contact events. Preliminary results confirm the technical feasibility of continuous monitoring in steep terrain and suggest possible elevational variation in diurnal visitors, alongside nocturnal activity by Geometridae moths. Camera-based observations provided higher functional resolution and revealed a different visitor assemblage than previous eDNA metabarcoding trials. This proof-of-concept establishes a methodological foundation for forthcoming multi-day monitoring campaigns and complements ongoing studies of the mating system and population-genetic analyses.

Climate change is reshaping weed population dynamics, creating non-stationary management challenges for which static decision rules are insufficient. This chapter presents and evaluates an open surveillance toolkit of artificial intelligence tools for recognizing and mapping Ambrosia artemisiifolia (common ragweed) at complementary spatial scales, tested across two phenological phases (seedling, September 2024; adult, December 2024) in a lentil paddock in central Chile. At the field scale, a YOLOv11 detection model coupled with Slicing Aided Hyper Inference achieved mAP50 of 0.886. Cross-domain experiments revealed that single-site models collapse catastrophically when deployed in new geographies (mAP50 dropping to 0.108), but multi-domain training recovers performance to 0.874. At the satellite scale, PRESTO foundation model embeddings correlated strongly with ground-truth weed density (r = 0.739); geographically weighted regression explained up to 91% of local density variance. All methods are released as the ragweed-ai-toolkit (https://github.com/agroia-lab/ragweed-ai-toolkit), a modular open-source Python package enabling adaptation to new species and geographies.