Drones are becoming increasingly valuable tools in wildlife studies due to their ability to access remote areas and offer high-resolution information with minimal human interference. Their application is, however, causing concern regarding wildlife disturbance. This review synthesizes the existing literature on how animals within terrestrial, aerial, and aquatic environments are impacted by drone disturbance in relation to operational variables, sensory stimulation, species-specific sensitivity, and physiological and behavioral responses. We found that drone altitude, speed, approach distance, and noise levels significantly influence wildlife responses, with some species exhibiting increased vigilance, flight responses, or physiological stress. Environmental context and visual cues are also involved in species detection of drones and disturbance thresholds. Although the short-term response to behavior change has been well documented, long-term consequences of repeated drone exposure remain poorly known. This paper identifies the necessity for continued research into drone–wildlife interactions, with an emphasis on the requirement to minimize disturbance by means of improved flight parameters and technology.

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.

Drones are becoming increasingly valuable tools in wildlife studies due to their ability to 1 access remote areas and offer high-resolution information with minimal human interference. Their 2 application is, however, causing concern regarding wildlife disturbance. This review synthesizes the 3 existing literature on how animals within terrestrial, aerial, and aquatic environments are impacted by 4 drone disturbance in relation to operational variables, sensory stimulation, species-specific sensitivity, 5 and physiological and behavioral responses. We found that drone altitude, speed, approach distance, 6 and noise levels significantly influence wildlife responses, with some species exhibiting increased 7 vigilance, flight responses, or physiological stress. Environmental context and visual cues are also 8 involved in species detection of drones and disturbance thresholds. Although the short-term response 9 to behaviour change has been well documented, long-term consequences of repeated drone exposure 10 remain poorly known. This paper identifies the necessity for continued research into drone-wildlife 11 interactions, with an emphasis on the requirement to minimize disturbance by means of improved 12 flight parameters and technology.

For many species, the ability to rapidly adapt to changes in seasonality is essential for long‐term survival. In the Arctic, seasonal moulting is a key life‐history event that provides year‐round camouflage and thermal protection. However, increased climatic variability of seasonal events can lead to phenological mismatch. In this study, we investigated whether winter‐white (white morph) and winter‐brown (blue morph) Arctic foxes (Vulpes lagopus) could adjust their winter‐to‐summer moult to match local environmental conditions. We used camera trap images spanning an eight‐year period to quantify the timing and rate of fur change in a polymorphic subpopulation in south‐central Norway. Seasonal snow cover duration and temperature governed the phenology of the spring moult. We observed a later onset and longer moulting duration with decreasing temperature and longer snow season. Additionally, white foxes moulted earlier than blue in years with shorter periods of snow cover and warmer temperatures. These results suggest that phenotypic plasticity allows Arctic foxes to modulate the timing and rate of their spring moult as snow conditions and temperatures fluctuate. With the Arctic warming at an unprecedented rate, understanding the capacity of polar species to physiologically adapt to a changing environment is urgently needed in order to develop adaptive conservation efforts. Moreover, we provide the first evidence for variations in the moulting phenology of blue and white Arctic foxes. Our study underlines the different intraspecific selective pressures that can exist in populations where several morphs co‐occur, and illustrates the importance of integrating morph‐based differences in future management strategies of such polymorphic species.