RSS-FED: Precision Agriculture in the AI Age.
This project will investigate the use of Precision Agriculture (PA) to estimate fertilizer needs for a field and/or crop. The project will aim to deliver algorithms/prototypes which can use satellite and drone technology to capture multi-spectral images and leverage this information to inform fertilizer requirements using state-of-the-art of Artificial Intelligence (AI) technology. The project will focus on 3 main areas: Satellite & Aerial Image Acquisition, Long-Term Soil Quality Estimation and In-Season Fertilizer Planning.
Our Research Team:
Dr Oscar Mendez
Lecturer in Robotics and Artificial Intelligence
Oscar is an internationally recognised researcher, interested in the fields of Machine Learning, Robotics and Computer Vision. His work focuses developing Machine Learning research that leverages concepts and ideas from fields like Remote Sensing and Agriculture and applies them to the areas of AI and Computer Vision. This creates algorithms that are better capable of understanding the world and making domain-specific predictions.
Mr Daniel Ayuba
Researcher in Remote Sensing and AI
Daniel is a postgraduate researcher seeking his PhD at the prestigious Centre for Vision, Speech, and Signal Processing (CVSSP) in the University Of Surrey. He has bachelor’s degree in Computer Science and a Masters’ degree in Satellite Applications with Data Science. Daniel has over 7 years of experience in developing technology. He started his career as a Software Engineer and later switched my career to Data Science.
Dr Belen Marti-Cardona
Senior Lecturer in Earth Observation and Hydrological Modelling
Belen is an award-winning researcher whose background includes engineering and modelling in the private and public sector. This provides her with a wide and practical picture of the engineering and Earth observation profession. She have an eye for connecting ideas and building work teams. Her research interests focus the use of remote sensing data (satellite and airborne) for hydrological and environmental applications, often exploiting the great synergies between varied geospatial data sources and digital twins or models, to go beyond what we can see with EO.