An official website of the United States government
Abstract Drones are increasingly popular for collecting behaviour data of group‐living animals, offering inexpensive and minimally disruptive observation methods. Imagery collected by drones can be rapidly analysed using computer vision techniques to extract information, including behaviour classification, habitat analysis and identification of individual animals. While computer vision techniques can rapidly analyse drone‐collected data, the success of these analyses often depends on careful mission planning that considers downstream computational requirements—a critical factor frequently overlooked in current studies.We present a comprehensive summary of research in the growing AI‐driven animal ecology (ADAE) field, which integrates data collection with automated computational analysis focused on aerial imagery for collective animal behaviour studies. We systematically analyse current methodologies, technical challenges and emerging solutions in this field, from drone mission planning to behavioural inference. We illustrate computer vision pipelines that infer behaviour from drone imagery and present the computer vision tasks used for each step. We map specific computational tasks to their ecological applications, providing a framework for future research design.Our analysis reveals AI‐driven animal ecology studies for collective animal behaviour using drone imagery focus on detection and classification computer vision tasks. While convolutional neural networks (CNNs) remain dominant for detection and classification tasks, newer architectures like transformer‐based models and specialized video analysis networks (e.g. X3D, I3D, SlowFast) designed for temporal pattern recognition are gaining traction for pose estimation and behaviour inference. However, reported model accuracy varies widely by computer vision task, species, habitats and evaluation metrics, complicating meaningful comparisons between studies.Based on current trends, we conclude semi‐autonomous drone missions will be increasingly used to study collective animal behaviour. While manual drone operation remains prevalent, autonomous drone manoeuvrers, powered by edge AI, can scale and standardise collective animal behavioural studies while reducing the risk of disturbance and improving data quality. We propose guidelines for AI‐driven animal ecology drone studies adaptable to various computer vision tasks, species and habitats. This approach aims to collect high‐quality behaviour data while minimising disruption to the ecosystem.
more »
« less
FINDeM : A CRISPR ‐based, molecular method for rapid, inexpensive and field‐deployable organism detection
Abstract The field of ecology has undergone a molecular revolution, with researchers increasingly relying on DNA‐based methods for organism detection. Unfortunately, these techniques often require expensive equipment, dedicated laboratory spaces and specialized training in molecular and computational techniques; limitations that may exclude field researchers, underfunded programmes and citizen scientists from contributing to cutting‐edge science.It is for these reasons that we have designed a simplified, inexpensive method for field‐based molecular organism detection—FINDeM (Field‐deployableIsothermalNucleotide‐basedDetectionMethod). In this approach, DNA is extracted using chemical cell lysis and a cellulose filter disc, followed by two body‐heat inducible reactions—recombinase polymerase amplification and a CRISPR‐Cas12a fluorescent reporter assay—to amplify and detect target DNA, respectively.Here, we introduce and validate FINDeM in detectingBatrachochytrium dendrobatidis, the causative agent of amphibian chytridiomycosis, and show that this approach can identify single‐digit DNA copies from epidermal swabs in under 1 h using low‐cost supplies and field‐friendly equipment.This research signifies a breakthrough in ecology, as we demonstrate a field‐deployable platform that requires only basic supplies (i.e. micropipettes, plastic consumables and a UV flashlight), inexpensive reagents (~$1.29 USD/sample) and emanated body heat for highly sensitive, DNA‐based organism detection. By presenting FINDeM in an ecological system with pressing, global biodiversity implications, we aim to not only highlight how CRISPR‐based applications promise to revolutionize organism detection but also how the continued development of such techniques will allow for additional, more diversely trained researchers to answer the most pressing questions in ecology.
more »
« less
- Award ID(s):
- 2120084
- PAR ID:
- 10512705
- Publisher / Repository:
- Methods in Ecology and Evolution
- Date Published:
- Journal Name:
- Methods in Ecology and Evolution
- Volume:
- 14
- Issue:
- 12
- ISSN:
- 2041-210X
- Page Range / eLocation ID:
- 3055 to 3067
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Fast mvSLOUCH : Multivariate Ornstein–Uhlenbeck‐based models of trait evolution on large phylogeniesAbstract ThePCMBase Rpackage is a powerful computational tool that enables efficient calculations of likelihoods for a wide range of phylogenetic Gaussian models.Taking advantage of it, we redesigned theRpackagemvSLOUCH.Here, we demonstrate how the new version of the package can be used to thoroughly examine the evolution and adaptation of traits in a large dataset of 1252 vascular plants through the use of multivariate Ornstein–Uhlenbeck processes.The results of our analysis demonstrate the ability of the modelling framework to distinguish between various alternative hypotheses regarding the evolution of functional traits in angiosperms.more » « less
-
Abstract Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with an abundance of data and knowledge to extract. These include extraction of metadata, species identification, and phenomic data. Ecological and evolutionary biologists are increasingly using complex, multi‐step processes on data. These processes often include machine learning techniques, often built by others, that are difficult to reuse by other members in a collaboration.We present a conceptual workflow model for machine learning applications using image data to extract biological knowledge in the emerging field of imageomics. We derive an implementation of this conceptual workflow for a specific imageomics application that adheres to FAIR principles as a formal workflow definition that allows fully automated and reproducible execution, and consists of reusable workflow components.We outline technologies and best practices for creating an automated, reusable and modular workflow, and we show how they promote the reuse of machine learning models and their adaptation for new research questions. This conceptual workflow can be adapted: it can be semi‐automated, contain different components than those presented here, or have parallel components for comparative studies.We encourage researchers—both computer scientists and biologists—to build upon this conceptual workflow that combines machine learning tools on image data to answer novel scientific questions in their respective fields.more » « less
-
Abstract Most biodiversity dynamics and ecosystem processes on land take place in microclimates that are decoupled from the climate as measured by standardised weather stations in open, unshaded locations. As a result, microclimate monitoring is increasingly being integrated in many studies in ecology and evolution.Overviews of the protocols and measurement methods related to microclimate are needed, especially for those starting in the field and to achieve more generality and standardisation in microclimate studies.Here, we present 10 practical guidelines for ground‐based research of terrestrial microclimates, covering methods and best practices from initial conceptualisation of the study to data analyses.Our guidelines encompass the significance of microclimates; the specifics of what, where, when and how to measure them; the design of microclimate studies; and the optimal approaches for analysing and sharing data for future use and collaborations. The paper is structured as a chronological guide, leading the reader through each step necessary to conduct a comprehensive microclimate study. At the end, we also discuss further research avenues and development in this field.With these 10 guidelines for microclimate monitoring, we hope to stimulate and advance microclimate research in ecology and evolution, especially under the pressing need to account for buffering or amplifying abilities of contrasting microhabitats in the context of global climate change.more » « less
-
Abstract Environmental DNA (eDNA) has revolutionized ecological research, particularly for biodiversity assessment in various environments, most notably aquatic media. Environmental DNA analysis allows for non‐invasive and rapid species detection across multiple taxonomic groups within a single sample, making it especially useful for identifying rare or invasive species. Due to dynamic hydrological processes, eDNA samples from running waters may represent biodiversity from broad contributing areas, which is convenient from a biomonitoring perspective but also challenging, as hydrological knowledge is required for meaningful biological interpretation. Hydrologists could also benefit from eDNA to address unsolved questions, particularly concerning water movement through catchments. While naturally occurring abiotic tracers have advanced our understanding of water age distribution in catchments, for example, current geochemical tracers cannot fully elucidate the timing and flow paths of water through landscapes. Conversely, biological tracers, owing to their immense diversity and interactions with the environment, could offer more detailed information on the sources and flow paths of water to the stream. The informational capacity of eDNA as a tracer, however, is determined by the ability to interpret the complex biological heterogeneity at a study site, which arguably requires both biological and hydrological expertise. As eDNA data has become increasingly available as part of biomonitoring campaigns, we argue that accompanying eDNA surveys with hydrological observations could enhance our understanding of both biological and hydrological processes; we identify opportunities, challenges, and needs for further interdisciplinary collaboration; and we highlight eDNA's potential as a bridge between hydrology and biology, which could foster both domains. This article is categorized under:Science of Water > Hydrological ProcessesScience of Water > MethodsWater and Life > Nature of Freshwater Ecosystemsmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1111/2041-210X.14236
