Emerging technologies for behavioral research in changing environments

Deep neural networks and stochastic methods for cognitive modeling of rat behavioral dynamics in T -mazes

Modeling animal decision-making requires mathematical rigor and computational analysis to capture underlying cognitive mechanisms. This study presents a cognitive model for rat decision-making behavior in T -mazes by combining stochastic methods with deep neural architectures. The model adapts Wyckoff's stochastic framework, originally grounded in Bush's discrimination learning theory, to describe probabilistic transitions between directional choices under reinforcement contingencies. The existence and uniqueness of solutions are demonstrated via fixed-point theorems, ensuring the formulation is well-posed. The asymptotic properties of the system are examined under boundary conditions to understand the convergence behavior of decision probabilities across trials. Empirical validation is performed using Monte Carlo simulations to compare expected trajectories with the model's predictive output. The dataset comprises spatial trajectory recordings of rats navigating toward food rewards under controlled experimental protocols. Trajectories are preprocessed through statistical filtering, augmented to address data imbalance, and embedded using t-SNE to visualize separability across behavioral states. A hybrid convolutional-recurrent neural network (CNN-LSTM) is trained on these representations and achieves a classification accuracy of 82.24%, outperforming conventional machine learning models, including support vector machines and random forests. In addition to discrete choice prediction, the network reconstructs continuous paths, enabling full behavioral sequence modeling from partial observations. The integration of stochastic dynamics and deep learning develops a computational basis for analyzing spatial decision-making in animal behavior. The proposed approach contributes to computational models of cognition by linking observable behavior to internal processes in navigational tasks.

Maintaining robust terrestrial ecological monitoring amid technological advancements

Long-term terrestrial biodiversity monitoring is crucial for understanding species and ecosystem responses to global change, yet it requires significant investment. Technological advancements offer opportunities for more efficient, scalable, and cost-effective monitoring, but transitioning to new methods presents significant risks to data integrity. Guidance for researchers and practitioners to manage these transitions, therefore, is critical. We present a novel seven-step framework and decision-making tool to guide the integration of new methods into established monitoring programs. The framework includes compatibility assessment, concurrent method cross-validation, and ongoing review, balancing the benefits of new technologies with the need to maintain dataset integrity. Our framework can help to ensure that new methods enhance the value and robustness of long-term biodiversity datasets while maintaining monitoring continuity.

Computer vision for primate behavior analysis in the wild

Advances in computer vision and increasingly widespread video-based behavioral monitoring are currently transforming how we study animal behavior. However, there is still a gap between the prospects and practical application, especially in videos from the wild. In this Perspective, we aim to present the capabilities of current methods for behavioral analysis, while at the same time highlighting unsolved computer vision problems that are relevant to the study of animal behavior. We survey state-of-the-art methods for computer vision problems relevant to the video-based study of individualized animal behavior, including object detection, multi-animal tracking, individual identification and (inter)action understanding. We then review methods for effort-efficient learning, one of the challenges from a practical perspective. In our outlook on the emerging field of computer vision for animal behavior, we argue that the field should develop approaches to unify detection, tracking, identification and (inter)action understanding in a single, video-based framework.

Understanding collective behavior in biological systems through potential field mechanisms

Collective behavior in biological systems emerges from local interactions among individuals, enabling groups to adapt to dynamic environments. Traditional modeling approaches, such as bottom-up and top-down models, have limitations in accurately representing these complex interactions. We propose a novel potential field mechanism that integrates local interactions and environmental influences to explain collective behavior. This study introduces dynamic potential fields, where individuals perceive and respond to local potential fields generated by environmental cues and other individuals. We develop a mathematical framework combining distributed learning and swarm control to simulate and analyze collective behavior under varying conditions. Our simulations span a variety of environmental conditions, including standard environments where organisms interact under typical conditions, high noise environments where interactions are disrupted by random fluctuations, high density environments with increased competition for space, high risk environments featuring areas of strong negative potential field, and multiple resource environments with varying degrees of resource availability. These simulations demonstrate the adaptability and resilience of biological groups to changing and challenging conditions. Results reveal how potential fields facilitate the emergence of stable and coordinated behaviors, providing insights into self-organization, cooperation, and competition in nature. This framework enhances our understanding of collective behavior and has implications for bio-robotics, distributed systems, and complex networks.

Maximizing biological insights from instruments attached to animals

Instruments attached to animals ('biologgers') have facilitated extensive discoveries about the patterns, causes, and consequences of animal behavior. Here, we present examples of how biologging can deepen our fundamental understanding of ecosystems and our applied understanding of global change impacts by enabling tests of ecological theory. Applying the iterative process of science to biologging has enabled a diverse set of insights, including social and experiential learning in long-distance migrants, state-dependent risk aversion in foraging predators, and resource abundance driving movement across taxa. Now, biologging is poised to tackle questions and refine ecological theories at increasing levels of complexity by integrating measurements from numerous individuals, merging datasets from multiple species and their environments, and spanning disciplines, including physiology, behavior and demography.

SARTAB, a scalable system for automated real-time behavior detection based on animal tracking and Region Of Interest analysis: validation on fish courtship behavior

Methods from Machine Learning (ML) and Computer Vision (CV) have proven powerful tools for quickly and accurately analyzing behavioral recordings. The computational complexity of these techniques, however, often precludes applications that require real-time analysis: for example, experiments where a stimulus must be applied in response to a particular behavior or samples must be collected soon after the behavior occurs. Here, we describe SARTAB (Scalable Automated Real-Time Analysis of Behavior), a system that achieves automated real-time behavior detection by continuously monitoring animal positions relative to behaviorally relevant Regions Of Interest (ROIs). We then show how we used this system to detect infrequent courtship behaviors in Pseudotropheus demasoni (a species of Lake Malawi African cichlid fish) to collect neural tissue samples from actively behaving individuals for multiomic profiling at single nucleus resolution. Within this experimental context, we achieve high ROI and animal detection accuracies (mAP@[.5 : .95] of 0.969 and 0.718, respectively) and 100% classification accuracy on a set of 32 manually selected behavioral clips. SARTAB is unique in that all analysis runs on low-cost, edge-deployed hardware, making it a highly scalable and energy-efficient solution for real-time experimental feedback. Although our solution was developed specifically to study cichlid courtship behavior, the intrinsic flexibility of neural network analysis ensures that our approach can be adapted to novel species, behaviors, and environments.

Cognitive and behavioral response of mosquitofish (Gambusia affinis) to environmental factors: Microplastics, predator cues, and detour design methods

Urban stream syndrome is the collective term used to describe the physical and ecological degradation of streams draining urban lands that poses substantial threats to freshwater ecosystems. Among various consequences of urban expansion, microplastic pollution and shifts in predator-prey dynamics are prominent alterations to natural habitat that could impact the cognitive and behavioral responses of aquatic species. To explore how symptoms of urban stream syndrome impact the cognitive and behavioral responses of fish, we conducted two experiments using a delayed detour test to measure risk-taking and inhibitory control in Gambusia affinis. In the first experiment, we hypothesized that G. affinis exposed to different concentrations of microplastics would show altered inhibitory control and risk-taking. In the second experiment, we hypothesized that exposure to predator chemical cues during the detour task would alter inhibitory control and risk-taking in G. affinis. We did not find significant differences in inhibitory control or risk-taking in G. affinis exposed to microplastics or predator cues. We then compared the effect size and confidence intervals (CI) of these results with published results that used the same detour test to study inhibitory control and risk-taking in G. affinis in response to different environmental conditions. Our investigations revealed that the CIs of the two studies presented here were larger than the CIs in the previously published studies. We consider potential changes to the experimental design that might have affected our ability to detect differences, such as the dimensions of the testing tanks. We also suggest extending the duration of the test to allow ample time for both exiting the starting chamber and solving the detour. We also propose considering the size and age of the species under study and adjusting the dimensions used in the detour paradigm design. Although our findings are specific to G. affinis, our results underscore the importance of considering aspects of the detour test design that are ecologically relevant to the study species when analysing cognitive and behavioral responses in fish. With our discussion, we contribute to the understanding of detour test methodologies and highlight potential ecological factors that could influence cognitive and behavioral outcomes.

Anthropogenic impacts at the interface of animal spatial and social behaviour

Human disturbance is contributing to widespread, global changes in the distributions and densities of wild animals. These anthropogenic impacts on wildlife arise from multiple bottom-up and top-down pathways, including habitat loss, resource provisioning, climate change, pollution, infrastructure development, hunting and our direct presence. Animal behaviour is an important mechanism linking these disturbances to population outcomes, although these behavioural pathways are often complex and can remain obscured when different aspects of behaviour are studied in isolation from one another. The spatial-social interface provides a lens for understanding how an animal's spatial and social environments interact to determine its spatial and social phenotype (i.e. measurable characteristics of an individual), and how these phenotypes interact and feed back to reshape environments. Here, we review studies of animal behaviour at the spatial-social interface to understand and predict how human disturbance affects animal movement, distribution and intraspecific interactions, with consequences for the conservation of populations and ecosystems. By understanding the spatial-social mechanisms linking human disturbance to conservation outcomes, we can better design management interventions to mitigate undesired consequences of disturbance.This article is part of the theme issue 'The spatial-social interface: a theoretical and empirical integration'.

Listening to animal behavior to understand changing ecosystems

Interpreting sound gives powerful insight into the health of ecosystems. Beyond detecting the presence of wildlife, bioacoustic signals can reveal their behavior. However, behavioral bioacoustic information is underused because identifying the function and context of animals' sounds remains challenging. A growing acoustic toolbox is allowing researchers to begin decoding bioacoustic signals by linking individual and population-level sensing. Yet, studies integrating acoustic tools for behavioral insight across levels of biological organization remain scarce. We aim to catalyze the emerging field of behavioral bioacoustics by synthesizing recent successes and rising analytical, logistical, and ethical challenges. Because behavior typically represents animals' first response to environmental change, we posit that behavioral bioacoustics will provide theoretical and applied insights into animals' adaptations to global change.

Leveraging AI to improve evidence synthesis in conservation

Systematic evidence syntheses (systematic reviews and maps) summarize knowledge and are used to support decisions and policies in a variety of applied fields, from medicine and public health to biodiversity conservation. However, conducting these exercises in conservation is often expensive and slow, which can impede their use and hamper progress in addressing the current biodiversity crisis. With the explosive growth of large language models (LLMs) and other forms of artificial intelligence (AI), we discuss here the promise and perils associated with their use. We conclude that, when judiciously used, AI has the potential to speed up and hopefully improve the process of evidence synthesis, which can be particularly useful for underfunded applied fields, such as conservation science.

Collective incentives reduce over-exploitation of social information in unconstrained human groups

Collective dynamics emerge from countless individual decisions. Yet, we poorly understand the processes governing dynamically-interacting individuals in human collectives under realistic conditions. We present a naturalistic immersive-reality experiment where groups of participants searched for rewards in different environments, studying how individuals weigh personal and social information and how this shapes individual and collective outcomes. Capturing high-resolution visual-spatial data, behavioral analyses revealed individual-level gains-but group-level losses-of high social information use and spatial proximity in environments with concentrated (vs. distributed) resources. Incentivizing participants at the group (vs. individual) level facilitated adaptation to concentrated environments, buffering apparently excessive scrounging. To infer discrete choices from unconstrained interactions and uncover the underlying decision mechanisms, we developed an unsupervised Social Hidden Markov Decision model. Computational results showed that participants were more sensitive to social information in concentrated environments frequently switching to a social relocation state where they approach successful group members. Group-level incentives reduced participants' overall responsiveness to social information and promoted higher selectivity over time. Finally, mapping group-level spatio-temporal dynamics through time-lagged regressions revealed a collective exploration-exploitation trade-off across different timescales. Our study unravels the processes linking individual-level strategies to emerging collective dynamics, and provides tools to investigate decision-making in freely-interacting collectives.

Coping with light pollution in urban environments: Patterns and challenges

Artificial light at night is a growing environmental problem that is especially pronounced in urban environments. Yet, impacts on urban wildlife have received scant attention and patterns and consequences are largely unknown. Here, I present a conceptual framework outlining the challenges species encounter when exposed to urban light pollution and how they may respond through plastic adjustments and genetic adaptation. Light pollution interferes with biological rhythms, influences behaviors, fragments habitats, and alters predation risk and resource abundance, which changes the diversity and spatiotemporal distribution of species and, hence, the structure and function of urban ecosystems. Furthermore, light pollution interacts with other urban disturbances, which can exacerbate negative effects on species. Given the rapid growth of urban areas and light pollution and the importance of healthy urban ecosystems for human wellbeing, more research is needed on the impacts of light pollution on species and the consequences for urban ecosystems.

No geographical differences in male mate choice in a widespread fish, Limia perugiae

Behavior, like most other traits, can have a spatial component, and variability of behavior at the population level is predicted. In this article, we explore male mate choice at this level. Male mate choice, while maybe not as common as female choice, is expected to evolve when males respond to significant variation in female quality and, for example, prefer females with higher fecundity. In fishes, higher fecundity is associated with larger body size, an easily measured trait. In this study, we investigated the presence of male mate choice for larger females in a widespread species of livebearing fish, Limia perugiae, while comparing preferences between populations. We hypothesized that environmental variation, for example, in the form of salinity, might result in population differences. Using dichotomous choice tests, we analyzed behavioral data for 80 individuals from 7 distinct populations from Hispaniola. We found that L. perugiae males significantly preferred large females, but there was no significant statistical variation between populations.

Time is of the essence: The importance of considering biological rhythms in an increasingly polluted world

Biological rhythms have a crucial role in shaping the biology and ecology of organisms. Light pollution is known to disrupt these rhythms, and evidence is emerging that chemical pollutants can cause similar disruption. Conversely, biological rhythms can influence the effects and toxicity of chemicals. Thus, by drawing insights from the extensive study of biological rhythms in biomedical and light pollution research, we can greatly improve our understanding of chemical pollution. This Essay advocates for the integration of biological rhythmicity into chemical pollution research to gain a more comprehensive understanding of how chemical pollutants affect wildlife and ecosystems. Despite historical barriers, recent experimental and technological advancements now facilitate the integration of biological rhythms into ecotoxicology, offering unprecedented, high-resolution data across spatiotemporal scales. Recognizing the importance of biological rhythms will be essential for understanding, predicting, and mitigating the complex ecological repercussions of chemical pollution.

Tracking technologies: advances driving new insights into monarch migration

Understanding the rules of how monarch butterflies complete their annual North American migration will be clarified by studying them within a movement ecology framework. Insect movement ecology is growing at a rapid pace due to the development of novel monitoring systems that allow ever-smaller animals to be tracked at higher spatiotemporal resolution for longer periods of time. New innovations in tracking hardware and associated software, including miniaturization, energy autonomy, data management, and wireless communication, are reducing the size and increasing the capability of next-generation tracking technologies, bringing the goal of tracking monarchs over their entire migration closer within reach. These tools are beginning to be leveraged to provide insight into different aspects of monarch biology and ecology, and to contribute to a growing capacity to understand insect movement ecology more broadly and its impact on human life.

Increasing ambient temperatures trigger shifts in activity patterns and temporal partitioning in a large carnivore guild

Shifts in species' interactions are implicated as an important proximate cause underpinning climate-change-related extinction. However, there is little empirical evidence on the pathways through which climate conditions, such as ambient temperature, impact community dynamics. The timing of activities is a widespread behavioural adaptation to environmental variability, and temporal partitioning is a key mechanism that facilitates coexistence, especially within large carnivore communities. We investigated temperature impacts on community dynamics through its influence on the diel activity of, and temporal partitioning amongst, four sympatric species of African large carnivores: lions (Panthera leo), leopards (Panthera pardus), cheetahs (Acinonyx jubatus) and African wild dogs (Lycaon pictus). Activity of all species was shaped by a combination of light availability and temperature, with most species becoming more nocturnal and decreasing activity levels with increasing temperatures. A nocturnal shift was most pronounced in cheetahs, the most diurnal species during median temperatures. This shift increased temporal overlap between cheetahs and other carnivore species by up to 15.92%, highlighting the importance of considering the responses of interacting sympatric species when inferring climate impacts on ecosystems. Our study provides evidence that temperature can significantly affect temporal partitioning within a carnivore guild by generating asymmetrical behavioural responses amongst functionally similar species.

Information Ecology: an integrative framework for studying animal behavior

Information is simultaneously a valuable resource for animals and a tractable variable for researchers. We propose the name Information Ecology to describe research focused on how individual animals use information to enhance fitness. An explicit focus on information in animal behavior is far from novel - we simply build on these ideas and promote a unified approach to how and why animals use information. The value of information to animals favors the theoretically rich adaptive approach of field-based research. Simultaneously, our ability to manipulate information lends itself to the strong methods of laboratory-based research. Information Ecology asks three questions: What information is available? How is it used (or not)? And, why is it used (or not)?

Effects of temperature on acoustic and visual courtship and reproductive success in the two-spotted goby Pomatoschistus flavescens

Fish are ectothermic and small changes in water temperature could greatly affect reproduction. The two-spotted goby is a small semi-pelagic species that uses visual and acoustic displays to mate. Here, we studied the effect of temperature (16 and 20 °C) on acoustic and visual courtship and associated reproductive success in 39 males. Temperature influenced male visual courtship performed outside the nest, but it did not influence calling rate and the number of laid eggs. Interestingly, the number of sounds (drums) was the sole predictor of spawning success. These findings suggest that exposure to different temperatures within the species' natural range affect courtship behaviour but not its reproductive success. We propose that finding the link between acoustic behaviour and reproduction in fishes offers the opportunity to monitor fish sounds both in the lab and in nature to learn how they respond to environmental changes and human impacts, namely global warming.

Elephants and algorithms: a review of the current and future role of AI in elephant monitoring

Artificial intelligence (AI) and machine learning (ML) present revolutionary opportunities to enhance our understanding of animal behaviour and conservation strategies. Using elephants, a crucial species in Africa and Asia's protected areas, as our focal point, we delve into the role of AI and ML in their conservation. Given the increasing amounts of data gathered from a variety of sensors like cameras, microphones, geophones, drones and satellites, the challenge lies in managing and interpreting this vast data. New AI and ML techniques offer solutions to streamline this process, helping us extract vital information that might otherwise be overlooked. This paper focuses on the different AI-driven monitoring methods and their potential for improving elephant conservation. Collaborative efforts between AI experts and ecological researchers are essential in leveraging these innovative technologies for enhanced wildlife conservation, setting a precedent for numerous other species.

Mechanisms of group-hunting in vertebrates

Group-hunting is ubiquitous across animal taxa and has received considerable attention in the context of its functions. By contrast much less is known about the mechanisms by which grouping predators hunt their prey. This is primarily due to a lack of experimental manipulation alongside logistical difficulties quantifying the behaviour of multiple predators at high spatiotemporal resolution as they search, select, and capture wild prey. However, the use of new remote-sensing technologies and a broadening of the focal taxa beyond apex predators provides researchers with a great opportunity to discern accurately how multiple predators hunt together and not just whether doing so provides hunters with a per capita benefit. We incorporate many ideas from collective behaviour and locomotion throughout this review to make testable predictions for future researchers and pay particular attention to the role that computer simulation can play in a feedback loop with empirical data collection. Our review of the literature showed that the breadth of predator:prey size ratios among the taxa that can be considered to hunt as a group is very large (<100 to >102 ). We therefore synthesised the literature with respect to these predator:prey ratios and found that they promoted different hunting mechanisms. Additionally, these different hunting mechanisms are also related to particular stages of the hunt (search, selection, capture) and thus we structure our review in accordance with these two factors (stage of the hunt and predator:prey size ratio). We identify several novel group-hunting mechanisms which are largely untested, particularly under field conditions, and we also highlight a range of potential study organisms that are amenable to experimental testing of these mechanisms in connection with tracking technology. We believe that a combination of new hypotheses, study systems and methodological approaches should help push the field of group-hunting in new directions.

Open questions in marine mammal sensory research

Although much research has focused on marine mammal sensory systems over the last several decades, we still lack basic knowledge for many of the species within this diverse group of animals. Our conference workshop allowed all participants to present recent developments in the field and culminated in discussions on current knowledge gaps. This report summarizes open questions regarding marine mammal sensory ecology and will hopefully serve as a platform for future research.