Drones: An ally in the sky to help save elephants!

University of Oxford

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Drone in use in Samburu National Reserve. Credit: @ Jane Wynyard / Save the Elephants

view more 

Credit: @ Jane Wynyard / Save the Elephants

Key Findings

• Drones can be a valuable, non-invasive tool for observing elephant families and aiding long-term conservation efforts.
• Elephants can habituate to drones - showing fewer signs of disturbance both during a single flight and after repeated exposures. Disturbance behaviours were 70% less likely on successive drone flights.
• Careful flight protocols matter - when flown high (120 m or above), with a downwind approach, and steadily, drones cause minimal stress.
• Just under half of all trials showed no signs of disturbance, and those that did quickly returned to levels comparable with pre-exposure.
• The findings have been published today (27 November) in Nature: Scientific Reports.

Nairobi, Kenya - Thursday, November 27 -  They say an elephant never forgets - and it turns out they can learn to adapt to drones!

Once seen as a source of alarm, drones are now proving to be surprisingly elephant-friendly and a valuable research tool. Previously, the use of drones in elephant conservation has mostly relied on their power to disturb: elephants reliably run from them, making them a useful tool to drive elephants from croplands.

Now, new work published today by Save the Elephants (STE) and the University of Oxford has shown that elephants can learn to ignore drones, a finding that could transform how scientists and conservationists monitor wildlife.

Drones, or Unmanned Aerial Vehicles (UAVs), have become increasingly important for wildlife research. With their buzzing propellers, which can sound like a swarm of bees, drones have been used to chase elephants from farms. But when flown in a way designed to minimise disturbance, elephants soon learn to ignore them.

And that’s good news for science. Ever since Iain Douglas-Hamilton pioneered the scientific study of wild elephant behaviour in the 1960s, observations on their interactions have been observed from alongside them, in vehicles, or in some cases on platforms. Now drones offer a completely new perspective on what is happening within a herd.

This new perspective offers the tantalising opportunity to precisely quantify for the first time how individuals in a group of elephants inter-relate in different situations. The on-board cameras and integrated sensors gather large amounts of data - data that AI-enabled software can search for patterns that have eluded human researchers until now.

The new study, published in Scientific Reports (https://doi.org/10.1038/s41598-025-25762-2) today, confirms that flying a drone high and steady changes the behaviour of elephants only temporarily, if the elephants react at all. Already the team has been given intriguing hints about the sleep habits of elephants under the cover of darkness, and are on the brink of releasing a tool that can automatically derive the age and sex of each individual in the group being observed.

The study, supported by the Colossal Foundation, combines STE’s 30+ years of long-term field expertise with cutting-edge technology to help deepen our understanding of complex species like elephants.

Save the Elephants’ CEO, Frank Pope, says: “Biodiversity is in crisis but we’re not standing still. New technologies are expanding our ability to perceive, analyse and understand the wild world in a way that was previously unthinkable. This study promises to open a new window onto how elephants work.”

The researchers conducted 35 quadcopter drone trials on 14 individually known elephant families in northern Kenya’s Samburu and Buffalo Springs National Reserves. About half showed signs of disturbance when first exposed - predominantly mild, such as lifting their trunks or pausing their activities - but these reactions diminished rapidly, within just six minutes, and were 70 percent less likely to recur in repeated flights. 

Lead author, Angus Carey-Douglas from Save the Elephants says, “The way in which the drone is flown is crucial. We found that not all elephants were disturbed, and those that were became less agitated both during a single flight and over repeated exposures. Additionally, our results suggest that these habituation effects may last over many months if not years, demonstrating the capacity for learning and adaptability for which elephants are already well known.”

This habituation means drones have potential as a non-invasive, cost-effective observation platform, helping scientists gather data about elephant movement, social interactions, and responses to environmental changes with minimal interference. Enhanced monitoring with drones is already revealing new behaviours, giving conservationists deeper insights into elephant lives and helping to shape more effective protection efforts.

Save the Elephants’ chairman and co-author, Professor Fritz Vollrath from Oxford University’s Department of Biology, notes: “This research demonstrates the power of a new and rapidly evolving technology that allows us to probe ever deeper into the secret lives of elephants. For example, the onboard thermal camera penetrates the darkness, opening up detailed studies of night-time behaviour and sleeping patterns.”

Matt James, Executive Director, Colossal Foundation says: "We are proud to partner with and support Save the Elephants in deploying cutting-edge technologies to protect elephants in the wild. This collaboration is a powerful example of how Colossal’s de-extinction innovations are already safeguarding living species today, demonstrating that the tools we’re developing to bring back the past are equally vital for protecting biodiversity today."

The researchers emphasise that while drones can be powerful tools for conservation (for instance in the study of marine mammals), their use around wildlife should always be strictly controlled. In Kenya, tourist and recreational drone flights are prohibited in national parks and reserves to protect animals from unnecessary stress. The drones in this study were operated under special permits issued by the Kenya Civil Aviation Authority and the Wildlife Research and Training Institute.

Read the full study (on 27 November)- Nature Scientific Reports: Elephant habituation to drones as a behavioural observation tool - here https://doi.org/10.1038/s41598-025-25762-2

For more images and video footage please click here. https://drive.google.com/drive/folders/18z2QmFTtoIfveio2p5z-MAd6krumY_xO?usp=share_link These images are for editorial puposes relating to the press release ONLY and MUST be credited (see captions file in folder). They MUST NOT be sold on to third parties

About Save the Elephants

Save the Elephants works to secure a future for elephants. Specialising in elephant  research, it provides scientific insights into elephant behaviour, intelligence, and long-distance movements and applies them to the challenges of elephant survival and harmonious coexistence with  humanity. High-tech tracking helps plan landscapes while low-tech beehive fences, among other tools, provide people /communities living with elephants with protection as well as income. Education and  outreach programmes share these insights with local communities as the true custodians of this rich  heritage. Save the Elephants (www.savetheelephants.org) runs the Elephant Crisis Fund  (www.elephantcrisisfund.org) in partnership with the Wildlife Conservation Network, providing flexible  and responsive support to NGOs combatting the ivory trade, promoting human-elephant coexistence,  and protecting elephant landscapes.

In September 2025, Save the Elephants was named the winner of the 20th BBVA Foundation Worldwide Award for Biodiversity Conservation, receiving international recognition for its groundbreaking and sustained contribution to protecting elephants across the African continent through its Elephant Crisis Fund (ECF).

About the University of Oxford

Oxford University has been placed number 1 in the Times Higher Education World University Rankings for the tenth year running, and ​number 3 in the QS World Rankings 2024. At the heart of this success are the twin-pillars of our ground-breaking research and innovation and our distinctive educational offer.

Oxford is world-famous for research and teaching excellence and home to some of the most talented people from across the globe. Our work helps the lives of millions, solving real-world problems through a huge network of partnerships and collaborations. The breadth and interdisciplinary nature of our research alongside our personalised approach to teaching sparks imaginative and inventive insights and solutions.

Through its research commercialisation arm, Oxford University Innovation, Oxford is the highest university patent filer in the UK and is ranked first in the UK for university spinouts, having created more than 300 new companies since 1988. Over a third of these companies have been created in the past five years. The university is a catalyst for prosperity in Oxfordshire and the United Kingdom, contributing around £16.9 billion to the UK economy in 2021/22, and supports more than 90,400 full time jobs.

About the Colossal Foundation

The Colossal Foundation is a 501(c)(3) dedicated to supporting the use of cutting-edge technologies for conservation efforts globally to help prevent extinction of keystone species. The organization deploys de-extinction technologies and support to empower partners in the field to reverse the extinction crisis. Learn more at www.ColossalFoundation.org

Drones are proving to be surprisingly elephant-friendly and a valuable research tool. Credit: @Jane Wynyard / Save the Elephants

Drone in use in Samburu National Reserve. Credit: @Jane Wynyard / Save the Elephants

Save the Elephants’s drone team in Samburu National Reserve. @Jane Wynyard / Save the Elephants

Scientific Reports

DOI

10.1038/s41598-025-25762-2 

Article Title

Elephant habituation to drones as a behavioural observation tool

Article Publication Date

27-Nov-2025

It’s a bird, it’s a drone, it’s both: AI tech monitors turkey behavior

Penn State

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

From the videos, the researchers took individual image frames and manually labeled the turkeys’ behaviors, including feeding, drinking, sitting, standing, perching, huddling and wing flapping.  

view more 

Credit: Penn State

UNIVERSITY PARK, Pa. — At a time when millions of Americans have turkey on their minds, a team of researchers led by an animal scientist at Penn State has successfully tested a new way for poultry producers to keep their turkeys in sight. 

Crucial for productivity and animal welfare, monitoring behavior and health of poultry animals on large, commercial farms is a costly, time-consuming and labor-intensive task. To help producers keep track of how the birds are behaving, the researchers tested a new method using a small drone equipped with a camera and computer vision — a form of artificial intelligence (AI) that enables recognition and processing of visual information — to automatically recognize what turkeys are doing.

Their study is available online now ahead of publication in the December issue of Poultry Science.

The research was the first to test whether a drone combined with a computer vision model could automatically detect different turkey behaviors from overhead video, according to study senior author Enrico Casella, assistant professor of data science for animal systems in the College of Agricultural Sciences. He also is affiliated with the Penn State Institute of Computational and Data Sciences.

“This work provides proof of concept that drones plus AI can potentially become an effective, low-labor method for monitoring turkey welfare in commercial production,” Casella said. “It lays the groundwork for more advanced, scalable systems in the future.”

The researchers used a commercially available drone with a regular color camera to record video four times a day of 160 young turkeys from five to 32 days old at the Penn State Poultry Education and Research Center. The drone’s trajectories were designed to ensure full area coverage from the camera footage during each flight.

From these videos, the researchers took individual image frames and manually labeled the turkeys’ behaviors. They created a dataset of over 19,000 instances of labeled behaviors, including feeding, drinking, sitting, standing, perching, huddling and wing flapping. Then they used the images to train, test and validate a computer vision model called YOLO — you only look once — commonly used to detect objects and actions in images.

The researchers tested several YOLO versions and found that the best model could correctly find 87% of all present behaviors and accurately detect specific behavior 98% of the time. These metrics are good, Casella pointed out — especially for behavior classification in a real farm environment, which often is visually messy and challenging.

“The study shows that a drone equipped AI system can accurately detect turkey behaviors,” he said. “This method could reduce labor demands, it could allow continuous, non-invasive monitoring of bird welfare in commercial farms and it may also reduce the need for constant human presence, lowering training and staffing burdens.”

Giulio Calderone, doctoral degree student in the Department of Agricultural, Food and Forest Sciences at the University of Palermo in Italy, was first author on the study. Contributing to the research at Penn State were John Boney, Vernon E. Norris Faculty Fellow of Poultry Nutrition; and Mireia Molins, graduate student in animal science; and Pietro Catania, professor of agricultural mechanics at the University of Palermo.

The research was funded by the U.S. Department of Agriculture’s National Institute of Food and Agriculture and supported by the Penn State Institute for Computational and Data Sciences.

---

Journal

Poultry Science

DOI

10.1016/j.psj.2025.106103 

Method of Research

Experimental study

Subject of Research

Animals

Article Title

Aerial monitoring of turkey behavior using unmanned aerial vehicles and computer vision

Article Publication Date

24-Nov-2025

 D.E.I.

UH researchers unveil X-ray breakthrough that captures 3 image-contrast types in a single shot

System could reveal early cancers, lung disease, hidden material defects and changes in porosity

University of Houston

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Mini Das is a Moores professor at the University of Houston's Cullen College of Engineering and College of Natural Sciences and Mathematics.

view more 

Credit: University of Houston

University of Houston researchers developed a new X-ray imaging method capable of revealing hidden features in a single shot, a breakthrough that could advance cancer detection, disease monitoring, security screening and material analysis.

This study, soon to be published in scientific journal Optica, introduces a system that captures far more detailed diagnostic information without requiring multiple exposures or complex mechanical movement. The research was led by physics researcher Jingcheng Yuan and Mini Das, Moores professor at UH’s Cullen College of Engineering and College of Natural Sciences and Mathematics.

Conventional X-ray and CT imaging rely solely on attenuation contrast, which shows how tissues and materials absorb X-rays.

While effective for bone and large-density differences, it struggles to reveal early-stage cancers or subtle changes in microstructures like the lung’s tiny air sacs. Emerging methods that aim to overcome these limitations need complex system designs and require long exposures to capture meaningful images, leading to higher radiation doses and difficulty to translate clinically.

“A lot of the methods being explored often need long imaging time because they require a system component to be moved multiple times — often over 10 or 20 times — to make these multiple image contrast,” Das said.

How It Works

To overcome these limitations, the UH team proposed and demonstrated new patent pending system designs and corresponding physics-based models.

The new configuration makes it possible to achieve three contrast types — attenuation, differential phase and dark field — from a single X-ray exposure. The design determines optimal placement of a single, slatted plate, or mask, between the X-ray source and detector.

The additional contrast types offer new insights:

• Differential phase, which Das introduced in a 2024 paper, shows how X-rays bend, enhancing visibility of boundaries, shapes and structural variations that are otherwise hard to see.
• Dark field captures how small-angle X-rays scatter from microstructures, revealing tiny structures such as lung air pockets or microscopic defects in materials.

Das said dark-field imaging may be especially promising for diagnosing lung diseases such as chronic obstructive pulmonary disease, where current imaging can’t detect the microstructural changes. One can also examine changes in lung cancer and their response to therapies.

“We know there will be benefit, but how much that will help clinicians diagnose, detect and follow up for therapy monitoring is an open avenue right now,” she said.

Why It Matters

The new single-shot and motion-free method produces images that are more informative, low-dose and faster — helping to lower patients’ dose of radiation, which can be especially beneficial for children and small animals.

The cost-effective design could be integrated into existing X-ray and CT systems with only minor modifications, making clinical translation feasible. The team’s next steps include adapting the system for small-animal studies and exploring clinical applications such as lung imaging and low-dose breast cancer screening.

“We expect that this will become practical, translatable,” Das said.

Beyond medicine, the technique could transform imaging for industries that rely on detecting internal defects or microstructures. Potential applications range from the petroleum industry and rock analysis, materials research and real-time monitoring of chemical or structural changes in engineered components.

Das has long been at the forefront of imaging innovation, previously advancing methods that investigated the wave nature of X-rays and applying photon-counting detectors with novel algorithms to allow for more precise 3D visualization.

Her motivation traces back to her early work in developing breast CTs where it became evident that the poor contrast in X-ray radiography and CT could not always reliably detect breast cancers. X-ray mammography has relied on the same contrast mechanism for over a century.

“This is the modality that millions of women are using today for breast screening around the world,” Das said. “I realized that this is really a big problem, so when I came to Houston for my position, one of my goals was to try to change this to see how we can contribute to this field by combining physics, optics and engineering.”

Das’s interdisciplinary research is funded through multiple agencies, including the National Science Foundation, Congressionally Directed Medical Research Programs and National Institutes of Health. She mentors students from physics, biomedical engineering and electrical engineering.

Das was also recently elected as a fellow of Optica, recognizing her distinguished contributions to the advancement of the field, and has been a fellow of the Society for Optics & Photonics (SPIE) since 2022.

---

Journal

Optica

From left: Professor Mini Das and researcher Jingcheng Yuan stand in front of a home-built X-ray unit at the University of Houston. Das and her team have developed a new X-ray imaging method capable of producing multi-contrast imaging. 

Mini Das, Moores professor at the University of Houston's Cullen College of Engineering and College of Natural Sciences and Mathematics, developed a new X-ray imaging method capable of revealing hidden features.

Credit

University of Houston