AI and Computer Vision for Wild Bee Monitoring and Sustainable Agriculture

About the project

About the Project Pollinating insects are essential to agriculture and biodiversity, yet monitoring wild bees in natural environments remains extremely difficult. Bees are small, fast-moving and visually diverse, and must be detected against complex vegetation under changing illumination, weather and seasonal conditions. At the same time, farmers and ecologists need scalable ways to understand which pollinators are present, when and where they are active, and whether interventions intended to support them are actually effective. This PhD will investigate how computer vision, machine learning and intelligent sensing can enable automated monitoring and understanding of wild pollinators in real agricultural environments . The student will join research connected to NEWBEE , a four-year Horizon Europe Marie Skłodowska-Curie Actions (MSCA) Staff Exchanges project coordinated by Durham University. NEWBEE brings together universities, technology companies, agricultural organisations, ecological researchers and other stakeholders to develop practical approaches for monitoring wild bees, understanding their behaviour and increasing their contribution to sustainable agriculture. The project combines AI-enhanced field monitoring with interventions designed to support and attract wild bees. Potential research topics include: computer vision for detecting, recognising and tracking small, fast-moving insects in complex outdoor environments fine-grained visual classification of wild bee species from challenging and incomplete observations multi-camera and multimodal sensing for monitoring pollinator activity across agricultural landscapes long-term tracking and spatiotemporal modelling of flower visitation and pollinator behaviour domain adaptation and generalisation across farms, crops, seasons, climates and countries combining visual information with environmental, weather and agricultural data to model pollinator activity The exact direction will be shaped around the student's interests and background. The aim is to develop new computer vision and machine learning methods with strong publication potential , while validating them on challenging real-world ecological and agricultural data rather than purely benchmark datasets. NEWBEE is developing field-based multi-camera observation systems to monitor wild bees visiting crops and flowers and link these observations with environmental and agricultural measurements. The research can also move beyond observation towards data-driven ecological intervention . NEWBEE will investigate approaches including flower and companion planting, nesting opportunities and natural sensory cues intended to increase wild-bee activity at agricultural sites. This creates opportunities to use AI not only to detect pollinators, but also to quantify behavioural changes, compare interventions, model plant-pollinator interactions and predict where and when particular approaches are likely to be effective. A major advantage of this PhD is access to NEWBEE's international research network. The consortium includes partners across the UK, Ukraine, Czechia, Belgium, Moldova, Spain, Bulgaria, Portugal, Italy, Vietnam, Argentina and Japan , offering opportunities to work with different researchers, species, crops, climates and agricultural environments. The PhD will therefore be highly interdisciplinary and internationally connected. Depending on the research direction, the student may work alongside experts in computer vision, machine learning, pollinator ecology, insect behaviour and cognition, agriculture, conservation, genomics, economics, policy and environmental law for a period of up to 12 months in total . As NEWBEE is an MSCA Staff Exchanges project, eligible PhD researchers can undertake research secondments with project partners. Subject to MSCA eligibility and project approval, costs associated with approved secondments will be supported by the project , in line with MSCA conditions. This provides an unusual opportunity for a PhD student to spend substantial periods working in international academic, agricultural and industrial research environments. Please note that this is a self-funded PhD opportunity. NEWBEE supports eligible research secondments but does not provide funding for PhD tuition fees or a student stipend. Supervision You will be supervised by Dr. Amir Atapour-Abarghouei ( Durham University Profile ), Associate Professor in Computer Vision and Machine Learning at the Department of Computer Science, Durham University . His research spans computer vision, deep learning, robotic perception, and neuromorphic computing , with a focus on efficient AI for autonomous systems. Dr. Atapour-Abarghouei has published in top-tier conferences and journals , including CVPR, ICCV, ECCV, ICML, IEEE Transactions on Image Processing, and IEEE Transactions on Multimedia . His work has been widely cited, demonstrating a strong impact on the fields of AI-driven vision, robotics, and machine learning. He has been involved in multiple national and international research projects , including EU-funded initiatives and collaborations with industry leaders in autonomous robotics, AI-driven perception, and deep learning efficiency. During the PhD study, you will receive comprehensive research training , including: Regular one-to-one supervision meetings to guide your research direction, develop research independence, and refine your technical and problem-solving skills. Support in academic writing and publishing , including help with designing experiments, writing papers and targeting leading conferences and journals in computer vision, machine learning and related areas. International and interdisciplinary research secondments of up to 12 months in total across the NEWBEE consortium. Access to advanced imaging and robotic platforms , including high-resolution camera systems, RGB and depth cameras, drones, mobile robotic platforms, Unitree G1 humanoid robots and Unitree Go2 quadruped robots, providing opportunities to develop and evaluate AI methods on real sensing and embodied systems. Access to a wide range of sensing technologies , including LiDAR, RADAR, inertial and localisation sensors, environmental sensors, EEG equipment and other multimodal sensing systems, supporting research in perception, sensor fusion and intelligent environmental monitoring. Training in interdisciplinary research and communication , including working with collaborators from computer science, biological sciences, ecology, agriculture, conservation, sustainability and policy, helping the student understand how advanced AI can be translated into practical scientific and agricultural applications. Durham University Durham University is a world top-100 university and is ranked the 6th in the UK. As a member university of the elite Russell Group, Durham University focuses on research excellence delivered by world-leading academics. It is the third oldest university in England, following Oxford and Cambridge, with the campus's Cathedral and Castle being a UNESCO world heritage. It is located at Durham in North East England – one of the safest cities in the UK with an affordable living cost. Entry Requirements A relevant undergraduate or master's degree with good scores. Knowledge of modern programming languages. Meet Durham's English requirements ( https://www.dur.ac.uk/study/international/entry-requirements/english-language-requirements/ ). How to Apply Please send an email with your resume, transcripts, and any supporting documents to Dr Amir Atapour-Abarghouei at amir.atapour-abarghouei@durham.ac.uk for an initial discussion.

Research areas