A Comprehensive Overview of Technologies for Species and Habitat Monitoring and Conservation

Pollinator-assisted plant phenotyping, selection, and breeding for crop resilience to abiotic stresses

Food security is threatened by climate change, with heat and drought being the main stresses affecting crop physiology and ecosystem services, such as plant-pollinator interactions. We hypothesize that tracking and ranking pollinators' preferences for flowers under environmental pressure could be used as a marker of plant quality for agricultural breeding to increase crop stress tolerance. Despite increasing relevance of flowers as the most stress sensitive organs, phenotyping platforms aim at identifying traits of resilience by assessing the plant physiological status through remote sensing-assisted vegetative indexes, but find strong bottlenecks in quantifying flower traits and in accurate genotype-to-phenotype prediction. However, as the transport of photoassimilates from leaves (sources) to flowers (sinks) is reduced in low-resilient plants, flowers are better indicators than leaves of plant well-being. Indeed, the chemical composition and amount of pollen and nectar that flowers produce, which ultimately serve as food resources for pollinators, change in response to environmental cues. Therefore, pollinators' preferences could be used as a measure of functional source-to-sink relationships for breeding decisions. To achieve this challenging goal, we propose to develop a pollinator-assisted phenotyping and selection platform for automated quantification of Genotype × Environment × Pollinator interactions through an insect geo-positioning system. Pollinator-assisted selection can be validated by metabolic, transcriptomic, and ionomic traits, and mapping of candidate genes, linking floral and leaf traits, pollinator preferences, plant resilience, and crop productivity. This radical new approach can change the current paradigm of plant phenotyping and find new paths for crop redomestication and breeding assisted by ecological decisions.

Comparing the cost-effectiveness of drones, camera trapping and passive acoustic recorders in detecting changes in koala occupancy

Quantifying the cost-effectiveness of alternative sampling methods is crucial for efficient biodiversity monitoring and detection of population trends. In this study, we compared the cost-effectiveness of three novel sampling methods for detecting changes in koala (Phascolarctos cinereus) occupancy: thermal drones, passive acoustic recorders and camera trapping. Specifically, we fitted single-season occupancy-detection models to data recorded from 46 sites in eight bioregions of New South Wales, Australia, between 2018 and 2022. We explored the effect of weather variables on daily detection probability for each method and, using these estimates, calculated the statistical power to detect 30%, 50% and 80% declines in koala occupancy. We calculated power for different combinations of sites (1-200) and repeat surveys (2-40) and developed a cost model that found the cheapest survey design that achieved 80% power to detect change. On average, detectability of koalas was highest with one 24-h period of acoustic surveys (0.32, 95% CI's: 0.26, 0.39) compared to a 25-ha flight of drone surveys (0.28, 95% 0.15, 0.48) or a 24-h period of camera trapping consisting of six cameras (0.019, 95% CI's: 0.014, 0.025). We found a negative quadratic relationship between detection probability and air temperature for all three methods. Our power and cost analysis suggested that 148 sites surveyed with acoustic recorders deployed for 14 days would be the cheapest method to sufficiently detect a 30% decline in occupancy with 80% power. We recommend passive acoustic recorders as the most efficient sampling method for monitoring koala occupancy compared to cameras or drones. Further comparative studies are needed to compare the relative effectiveness of these methods and others when the monitoring objective is to detect change in koala abundance over time.

Soundscape Characterization Using Autoencoders and Unsupervised Learning

Passive acoustic monitoring (PAM) through acoustic recorder units (ARUs) shows promise in detecting early landscape changes linked to functional and structural patterns, including species richness, acoustic diversity, community interactions, and human-induced threats. However, current approaches primarily rely on supervised methods, which require prior knowledge of collected datasets. This reliance poses challenges due to the large volumes of ARU data. In this work, we propose a non-supervised framework using autoencoders to extract soundscape features. We applied this framework to a dataset from Colombian landscapes captured by 31 audiomoth recorders. Our method generates clusters based on autoencoder features and represents cluster information with prototype spectrograms using centroid features and the decoder part of the neural network. Our analysis provides valuable insights into the distribution and temporal patterns of various sound compositions within the study area. By utilizing autoencoders, we identify significant soundscape patterns characterized by recurring and intense sound types across multiple frequency ranges. This comprehensive understanding of the study area's soundscape allows us to pinpoint crucial sound sources and gain deeper insights into its acoustic environment. Our results encourage further exploration of unsupervised algorithms in soundscape analysis as a promising alternative path for understanding and monitoring environmental changes.

Novel community data in ecology-properties and prospects

New technologies for monitoring biodiversity such as environmental (e)DNA, passive acoustic monitoring, and optical sensors promise to generate automated spatiotemporal community observations at unprecedented scales and resolutions. Here, we introduce 'novel community data' as an umbrella term for these data. We review the emerging field around novel community data, focusing on new ecological questions that could be addressed; the analytical tools available or needed to make best use of these data; and the potential implications of these developments for policy and conservation. We conclude that novel community data offer many opportunities to advance our understanding of fundamental ecological processes, including community assembly, biotic interactions, micro- and macroevolution, and overall ecosystem functioning.

Evaluating community-wide temporal sampling in passive acoustic monitoring: A comprehensive study of avian vocal patterns in subtropical montane forests

Background

From passive acoustic monitoring (PAM) recordings, the vocal activity rate (VAR), vocalizations per unit of time, can be calculated and is essential for assessing bird population abundance. However, VAR is subject to influences from a range of factors, including species and environmental conditions. Identifying the optimal sampling design to obtain representative acoustic data for VAR estimation is crucial for research objectives. PAM commonly uses temporal sampling strategies to decrease the volume of recordings and the resources needed for audio data management. Yet, the comprehensive impact of this sampling approach on VAR estimation remains insufficiently explored.

Methods

In this study, we used vocalizations extracted from recordings of 12 bird species, taken at 14 PAM stations situated in subtropical montane forests over a four-month period, to assess the impact of temporal sampling on VAR across three distinct scales: short-term periodic, diel, and hourly. For short-term periodic sampling analysis, we employed hierarchical clustering analysis (HCA) and the coefficient of variation (CV). Generalized additive models (GAMs) were utilized for diel sampling analysis, and we determined the average difference in VAR values per minute for the hourly sampling analysis.

Results

We identified significant day and species-specific VAR fluctuations. The survey season was divided into five segments; the earliest two showed high variability and are best avoided for surveys. Data from days with heavy rain and strong winds showed reduced VAR values and should be excluded from analysis. Continuous recordings spanning at least seven days, extending to 14 days is optimal for minimizing sampling variance. Morning chorus recordings effectively capture the majority of bird vocalizations, and hourly sampling with frequent, shorter intervals aligns closely with continuous recording outcomes.

Conclusions

While our findings are context-specific, they highlight the significance of strategic sampling in avian monitoring, optimizing resource utilization and enhancing the breadth of monitoring efforts.

Nature 4.0: A networked sensor system for integrated biodiversity monitoring

Ecosystem functions and services are severely threatened by unprecedented global loss in biodiversity. To counteract these trends, it is essential to develop systems to monitor changes in biodiversity for planning, evaluating, and implementing conservation and mitigation actions. However, the implementation of monitoring systems suffers from a trade-off between grain (i.e., the level of detail), extent (i.e., the number of study sites), and temporal repetition. Here, we present an applied and realized networked sensor system for integrated biodiversity monitoring in the Nature 4.0 project as a solution to these challenges, which considers plants and animals not only as targets of investigation, but also as parts of the modular sensor network by carrying sensors. Our networked sensor system consists of three main closely interlinked components with a modular structure: sensors, data transmission, and data storage, which are integrated into pipelines for automated biodiversity monitoring. We present our own real-world examples of applications, share our experiences in operating them, and provide our collected open data. Our flexible, low-cost, and open-source solutions can be applied for monitoring individual and multiple terrestrial plants and animals as well as their interactions. Ultimately, our system can also be applied to area-wide ecosystem mapping tasks, thereby providing an exemplary cost-efficient and powerful solution for biodiversity monitoring. Building upon our experiences in the Nature 4.0 project, we identified ten key challenges that need to be addressed to better understand and counteract the ongoing loss of biodiversity using networked sensor systems. To tackle these challenges, interdisciplinary collaboration, additional research, and practical solutions are necessary to enhance the capability and applicability of networked sensor systems for researchers and practitioners, ultimately further helping to ensure the sustainable management of ecosystems and the provision of ecosystem services.

Situational social influence leading to non-compliance with conservation rules

It is well established that the decisions that we make can be strongly influenced by the behaviour of others. However, testing how social influence can lead to non-compliance with conservation rules during an individual's decision-making process has received little research attention. We synthesise advances in understanding of conformity and rule-breaking in individuals and in groups, and take a situational approach to studying the social dynamics and ensuing social identity changes that can lead to non-compliant decision-making. We focus on situational social influence contagion that are copresent (i.e., same space and same time) or trace-based (i.e., behavioural traces in the same space). We then suggest approaches for testing how situational social influence can lead to certain behaviours in non-compliance with conservation rules.

Monitoring Endangered and Rare Wildlife in the Field: A Foundation Deep Learning Model Integrating Human Knowledge for Incremental Recognition with Few Data and Low Cost

Intelligent monitoring of endangered and rare wildlife is important for biodiversity conservation. In practical monitoring, few animal data are available to train recognition algorithms. The system must, therefore, achieve high accuracy with limited resources. Simultaneously, zoologists expect the system to be able to discover unknown species to make significant discoveries. To date, none of the current algorithms have these abilities. Therefore, this paper proposed a KI-CLIP method. Firstly, by first introducing CLIP, a foundation deep learning model that has not yet been applied in animal fields, the powerful recognition capability with few training resources is exploited with an additional shallow network. Secondly, inspired by the single-image recognition abilities of zoologists, we incorporate easily accessible expert description texts to improve performance with few samples. Finally, a simple incremental learning module is designed to detect unknown species. We conducted extensive comparative experiments, ablation experiments, and case studies on 12 datasets containing real data. The results validate the effectiveness of KI-CLIP, which can be trained on multiple real scenarios in seconds, achieving in our study over 90% recognition accuracy with only 8 training samples, and over 97% with 16 training samples. In conclusion, KI-CLIP is suitable for practical animal monitoring.

Digital twins: dynamic model-data fusion for ecology

Digital twins (DTs) are an emerging phenomenon in the public and private sectors as a new tool to monitor and understand systems and processes. DTs have the potential to change the status quo in ecology as part of its digital transformation. However, it is important to avoid misguided developments by managing expectations about DTs. We stress that DTs are not just big models of everything, containing big data and machine learning. Rather, the strength of DTs is in combining data, models, and domain knowledge, and their continuous alignment with the real world. We suggest that researchers and stakeholders exercise caution in DT development, keeping in mind that many of the strengths and challenges of computational modelling in ecology also apply to DTs.

Systematic review of machine learning methods applied to ecoacoustics and soundscape monitoring

Soundscape ecology is a promising area that studies landscape patterns based on their acoustic composition. It focuses on the distribution of biotic and abiotic sounds at different frequencies of the landscape acoustic attribute and the relationship of said sounds with ecosystem health metrics and indicators (e.g., species richness, acoustic biodiversity, vectors of structural change, gradients of vegetation cover, landscape connectivity, and temporal and spatial characteristics). To conduct such studies, researchers analyze recordings from Acoustic Recording Units (ARUs). The increasing use of ARUs and their capacity to record hours of audio for months at a time have created a need for automatic processing methods to reduce time consumption, correlate variables implicit in the recordings, extract features, and characterize sound patterns related to landscape attributes. Consequently, traditional machine learning methods have been commonly used to process data on different characteristics of soundscapes, mainly the presence-absence of species. In addition, it has been employed for call segmentation, species identification, and sound source clustering. However, some authors highlight the importance of the new approaches that use unsupervised deep learning methods to improve the results and diversify the assessed attributes. In this paper, we present a systematic review of machine learning methods used in the field of ecoacoustics for data processing. It includes recent trends, such as semi-supervised and unsupervised deep learning methods. Moreover, it maintains the format found in the reviewed papers. First, we describe the ARUs employed in the papers analyzed, their configuration, and the study sites where the datasets were collected. Then, we provide an ecological justification that relates acoustic monitoring to landscape features. Subsequently, we explain the machine learning methods followed to assess various landscape attributes. The results show a trend towards label-free methods that can process the large volumes of data gathered in recent years. Finally, we discuss the need to adopt methods with a machine learning approach in other biological dimensions of landscapes.

Real-time biodiversity analysis using deep-learning algorithms on mobile robotic platforms

Ecological biodiversity is declining at an unprecedented rate. To combat such irreversible changes in natural ecosystems, biodiversity conservation initiatives are being conducted globally. However, the lack of a feasible methodology to quantify biodiversity in real-time and investigate population dynamics in spatiotemporal scales prevents the use of ecological data in environmental planning. Traditionally, ecological studies rely on the census of an animal population by the "capture, mark and recapture" technique. In this technique, human field workers manually count, tag and observe tagged individuals, making it time-consuming, expensive, and cumbersome to patrol the entire area. Recent research has also demonstrated the potential for inexpensive and accessible sensors for ecological data monitoring. However, stationary sensors collect localised data which is highly specific on the placement of the setup. In this research, we propose the methodology for biodiversity monitoring utilising state-of-the-art deep learning (DL) methods operating in real-time on sample payloads of mobile robots. Such trained DL algorithms demonstrate a mean average precision (mAP) of 90.51% in an average inference time of 67.62 milliseconds within 6,000 training epochs. We claim that the use of such mobile platform setups inferring real-time ecological data can help us achieve our goal of quick and effective biodiversity surveys. An experimental test payload is fabricated, and online as well as offline field surveys are conducted, validating the proposed methodology for species identification that can be further extended to geo-localisation of flora and fauna in any ecosystem.

Hearing to the Unseen: AudioMoth and BirdNET as a Cheap and Easy Method for Monitoring Cryptic Bird Species

The efficient analyses of sound recordings obtained through passive acoustic monitoring (PAM) might be challenging owing to the vast amount of data collected using such technique. The development of species-specific acoustic recognizers (e.g., through deep learning) may alleviate the time required for sound recordings but are often difficult to create. Here, we evaluate the effectiveness of BirdNET, a new machine learning tool freely available for automated recognition and acoustic data processing, for correctly identifying and detecting two cryptic forest bird species. BirdNET precision was high for both the Coal Tit (Peripatus ater) and the Short-toed Treecreeper (Certhia brachydactyla), with mean values of 92.6% and 87.8%, respectively. Using the default values, BirdNET successfully detected the Coal Tit and the Short-toed Treecreeper in 90.5% and 98.4% of the annotated recordings, respectively. We also tested the impact of variable confidence scores on BirdNET performance and estimated the optimal confidence score for each species. Vocal activity patterns of both species, obtained using PAM and BirdNET, reached their peak during the first two hours after sunrise. We hope that our study may encourage researchers and managers to utilize this user-friendly and ready-to-use software, thus contributing to advancements in acoustic sensing and environmental monitoring.

ForageFeeder: A low-cost open source feeder for randomly distributing food

Automated feeders have long fed mice, livestock, and poultry, but are incapable of feeding zoo animals such as gorillas. In captivity, gorillas eat cut vegetables and fruits in pieces too large to be dispensed by automated feeders. Consequently, captive gorillas are fed manually at set times and locations, keeping them from the exercise and enrichment that accompanies natural foraging. We designed and built ForageFeeder, an automated gorilla feeder that spreads food at random intervals throughout the day. ForageFeeder is an open source and easy to manufacture and modify device, making the feeder more accessible for zoos. The design presented here reduces manual labor for zoo staff and may be a useful tool for studies of animal ethology.

Towards the fully automated monitoring of ecological communities

High-resolution monitoring is fundamental to understand ecosystems dynamics in an era of global change and biodiversity declines. While real-time and automated monitoring of abiotic components has been possible for some time, monitoring biotic components-for example, individual behaviours and traits, and species abundance and distribution-is far more challenging. Recent technological advancements offer potential solutions to achieve this through: (i) increasingly affordable high-throughput recording hardware, which can collect rich multidimensional data, and (ii) increasingly accessible artificial intelligence approaches, which can extract ecological knowledge from large datasets. However, automating the monitoring of facets of ecological communities via such technologies has primarily been achieved at low spatiotemporal resolutions within limited steps of the monitoring workflow. Here, we review existing technologies for data recording and processing that enable automated monitoring of ecological communities. We then present novel frameworks that combine such technologies, forming fully automated pipelines to detect, track, classify and count multiple species, and record behavioural and morphological traits, at resolutions which have previously been impossible to achieve. Based on these rapidly developing technologies, we illustrate a solution to one of the greatest challenges in ecology: the ability to rapidly generate high-resolution, multidimensional and standardised data across complex ecologies.

Conceptualizing the 3D niche and vertical space use

Spatial partitioning in ecological communities has predominantly been described in two dimensions, yet habitat is complex and 3D. Complex space use mediates community structure and interaction strength by expanding spatial, temporal, and dietary dimensions. Vertical stratification of resources provides opportunities for novel specializations, creating a 3D niche. Competition and predation are mediated by 3D space use, as individuals use the vertical axis to access prey, flee predators, or avoid competitors. The 3D niche is important for long-term conservation strategies as species must navigate tradeoffs in habitat use between strata-specific threats and suboptimal habitat patches. Ultimately, elucidating the 3D niche has implications for protected area management and corridor design that directly influence species persistence and ecosystem function in a rapidly changing world.

A practical approach with drones, smartphone and tracking tags for potential real-time tracking animal

In recent years, drones are increasingly used for fauna monitoring and wildlife tracking; however, the application of drones for tracking wildlife is restricted to those users with the technical capacity to develop such systems. We explore the potential of wildlife tracking with drones by using a system consisting of a multirotor drone, smartphones, and commercial tracking devices via Bluetooth and Ultra-Wide Band (UWB) off-the-shelf that is easy to use by non-specialists. We present the system configuration, explore the operational parameters that can affect detection capabilities, and test the effectiveness of the system in locating targets by simulating target animals in savanna and forest environments. The self-contained tracking system was built without the need for hardware or software customization. From 40 tracking flights carried out in the Cerrado biome, we obtained a detection rate of 90% in savanna and 40% in forest areas. Considering the moving tests (N = 20) the detection rates were 90% in the savanna and 30% in the forest areas. The spatial accuracy obtained by the system was 14.61 m, being significantly more accurate in savanna areas (x̄ = 10.53) than in forest areas (x̄ = 13.06). This approach to wildlife tracking facilitates the use of drones by non-specialists and at an affordable cost for conservation projects with limited resources. The reduced size of the tags, the long battery life and the reduced cost in relation to GPS-tags opens up a range of opportunities for tracking small to large fauna present in this type of vegetation.

Perspectives in machine learning for wildlife conservation

Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological understanding, but are limited by current processing approaches which inefficiently distill data into relevant information. We argue that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge. Incorporating machine learning into ecological workflows could improve inputs for ecological models and lead to integrated hybrid modeling tools. This approach will require close interdisciplinary collaboration to ensure the quality of novel approaches and train a new generation of data scientists in ecology and conservation.

Triton Field Trials: Promoting Consistent Environmental Monitoring Methodologies for Marine Energy Sites

Uncertainty surrounding the potential environmental impacts of marine energy (ME) has resulted in extensive and expensive environmental monitoring requirements for ME deployments. Recently, there have been more ME deployments and associated environmental data collection efforts, but no standardized methodologies for data collection. This hinders the use of previously collected data to inform new ME project permitting efforts. Triton Field Trials (TFiT), created at the Pacific Northwest National Laboratory by the United States (U.S.) Department of Energy, explores ways to promote more consistent environmental data collection and enable data transferability across ME device types and locations. Documents from 118 previous ME projects or ME-related research studies in the U.S. and internationally were reviewed to identify the highest priority stressor–receptor relationships to be investigated and the technologies and methodologies used to address them. Thirteen potential field sites were assessed to determine suitable locations for testing the performance of relevant monitoring technologies. This introductory paper provides an overview of how priority research areas and associated promising technologies were identified as well as how testing locations were identified for TFiT activities. Through these scoping efforts, TFiT focused on four activity areas: collision risk, underwater noise, electromagnetic fields, and changes in habitat. Technologies and methodologies were tested at field sites in Alaska, Washington, California, and New Hampshire. Detailed information on the effectiveness of the identified methodologies and specific recommendations for each of the four focus areas are included in the companion papers in this Special Issue.

Unlocking the Potential of Deep Learning for Migratory Waterbirds Monitoring Using Surveillance Video

Estimates of migratory waterbirds population provide the essential scientific basis to guide the conservation of coastal wetlands, which are heavily modified and threatened by economic development. New equipment and technology have been increasingly introduced in protected areas to expand the monitoring efforts, among which video surveillance and other unmanned devices are widely used in coastal wetlands. However, the massive amount of video records brings the dual challenge of storage and analysis. Manual analysis methods are time-consuming and error-prone, representing a significant bottleneck to rapid data processing and dissemination and application of results. Recently, video processing with deep learning has emerged as a solution, but its ability to accurately identify and count waterbirds across habitat types (e.g., mudflat, saltmarsh, and open water) is untested in coastal environments. In this study, we developed a two-step automatic waterbird monitoring framework. The first step involves automatic video segmentation, selection, processing, and mosaicking video footages into panorama images covering the entire monitoring area, which are subjected to the second step of counting and density estimation using a depth density estimation network (DDE). We tested the effectiveness and performance of the framework in Tiaozini, Jiangsu Province, China, which is a restored wetland, providing key high-tide roosting ground for migratory waterbirds in the East Asian–Australasian flyway. The results showed that our approach achieved an accuracy of 85.59%, outperforming many other popular deep learning algorithms. Furthermore, the standard error of our model was very small (se = 0.0004), suggesting the high stability of the method. The framework is computing effective—it takes about one minute to process a theme covering the entire site using a high-performance desktop computer. These results demonstrate that our framework can extract ecologically meaningful data and information from video surveillance footages accurately to assist biodiversity monitoring, fulfilling the gap in the efficient use of existing monitoring equipment deployed in protected areas.

Coproduce Conservation Technology With Conservation Decision Makers and Practitioners to Increase Its Impact

Addressing the biodiversity crisis will mean developing and adopting new resources and methods that effectively improve public conservation efforts. Technologies have a long track record of increasing the efficiency of carrying out time-consuming tasks or even making new feats possible, and if applied thoughtfully, can serve as a key means of strengthening conservation outcomes. Yet technology development sometimes proceeds without clear mechanisms for application and scaling, or key adopters like government agencies are not able to use the technologies. To overcome these discrepancies, we recommend the use of a coproduction model of conservation technology development that starts from detailed knowledge of conservation laws, regulations, policies, and their implementation; identifies choke points in those processes amenable to technological solutions; and then develops those solutions while integrating existing users and needs. To illustrate the model, we describe three tools recently developed to help improve the efficiency and effectiveness of implementing the U.S. Endangered Species Act. We also highlight several outstanding questions and challenges that the broad conservation technology and policy communities may help address.

Modular E-Collar for Animal Telemetry: An Animal-Centered Design Proposal

Animal telemetry is a subject of great potential and scientific interest, but it shows design-dependent problems related to price, flexibility and customization, autonomy, integration of elements, and structural design. The objective of this paper is to provide solutions, from the application of design, to cover the niches that we discovered by reviewing the scientific literature and studying the market. The design process followed to achieve the objective involved a development based on methodologies and basic design approaches focused on the human experience and also that of the animal. We present a modular collar that distributes electronic components in several compartments, connected, and powered by batteries that are wirelessly recharged. Its manufacture is based on 3D printing, something that facilitates immediacy in adaptation and economic affordability. The modularity presented by the proposal allows for adapting the size of the modules to the components they house as well as selecting which specific modules are needed in a project. The homogeneous weight distribution is transferred to the comfort of the animal and allows for a better integration of the elements of the collar. This device substantially improves the current offer of telemetry devices for farming animals, thanks to an animal-centered design process.