p
Conservation AI is a unique interdisciplinary project with researchers from computer science, astrophysics, and conservation biology. By harnessing the knowledge from these varying fields we aim to develop a platform and associated hardware that will bring benefits to the conservation community.
Paul Fergus is a Professor in Machine Learning. Paul's main research interests include machine learning for detecting and predicting preterm births. He is also interested in the detection of foetal hypoxia, electroencephalogram seizure classification and bioinformatics (polygenetic obesity, Type II diabetes and multiple sclerosis). Paul has a keen interest in conservation and is currently looking at the use of machine learning to solve different conservation-related problems. He has competitively won external grants to support his research from HEFCE, Royal Academy of Engineering, Innovate UK, Knowledge Transfer Partnership, North West Regional Innovation Fund and Bupa. Before his academic career Paul was a senior software engineer in industry for six years developing bespoke solutions for a number of large organisations.
Carl Chalmers is a Reader in Machine Learning and Applied Artificial Intelligence in the Department of Computer Science at Liverpool John Moores University. Carl's main research interests includes machine learning, computer vision, high performance computing and data visualisation. In addition, he is also working in the area of high-performance computing and cloud computing to support and improve existing machine learning approaches, while facilitating application integration. He is currently applying is knowledge and expertise of large-scale machine learning deployments to solve some of the pressing issues faced by conservation organisations. He has won multiple grant awards and has seen international recognition for his research in the area of machine learning. He currently leads a group of machine learning practitioners which includes academics, Post docs, PhD students and industry partners. Before his academic career Carl spent over 8 years in industry developing a wide variety of different applications.
Serge Wich is a professor at Liverpool John Moores University who has almost three decades of experience in animal behaviour, ecology, and conservation. Since 2011 he has been using drones to support conservation work and he is a co-founder of conservationdrones.org. Serge has a keen interest in using technology for conservation.
Steve Longmore is a professor in the Astrophysics Research Institute, whose research aims to understand how the Universe evolves over cosmic time to produce the spectacular variety of stars, planets and life we see today. He has a keen interest in applying astrophysics techniques to tackle problems closer to home, such as conservation of endangered species, search and rescue, or tackling peat fires that are a major contributor to climate change.
Naomi Davies is the Research and Conservation Officer at Knowsley Safari. Naomi conducted her master’s degree in Wildlife Conservation and Drone Technology through Liverpool John Moores University and has since been involved in a wide range of conservation research predominantly in the UK and South East Asia to benefit both captive and wild populations. The Conservation AI team have been working with Naomi to monitor the accessible and diverse range of animals available at Knowsley Safari.
Chris Sutherland is a Statistical Ecologists in the multidisciplinary Centre for Research into Ecological and Environmental Modelling (CREEM) at the University of St Andrews. Chris’s interests span ecology, statistics, and applied wildlife conservation and management, and more recently in innovative methods for wildlife and biodiversity monitoring. This includes the use of remote sensors to collect ecological data, the development and application of machine learning classifiers for data processing, and the development and application of ecologically realistic statistical methods. His current research focus within Conservation AI is the development of efficient and accessible data-to-decision pipelines for sensor data.