Steven Reece
INTRODUCTION
Steven Reece is a senior researcher in machine learning in the Engineering Science Department, Oxford University, a Turing Fellow at the Alan Turing Institute and an EPSRC funded Researcher in Residence at the Satellite Applications Catapult. He has a PhD from Oxford University and over 25 years research and consultancy experience in machine learning. He has developed both Bayesian and non-Bayesian approaches to reasoning with uncertainty that have been applied to fault correction of NASA astrophysics data, multi-robot terrain mapping, fault detection, social network analysis, sensor modelling, target tracking and big data economic forecasting. With a passion for foundational machine learning methods and finding solutions to both social and environmental problems, he now leads the Disaster Management and Environmental Protection Research Group within the wider Machine Learning Research Group. His group engages in information centred multi-disciplinary research and co-creation with academic, NGO, GO and commercial partners. Current work focusses on the intersection of Bayesian and deep learning methods for heterogeneous data fusion and scalable human-agent computation, including crowdsourced data interpretation. Steve’s group works closely with disaster response organisations and has developed and deployed satellite imagery and text analysis tools that have provided the UN, FEMA and NGOs with damage situation maps immediately following natural disasters. The group also works with hydrometeorological experts on drought impact in East Africa and commercial maritime disaster prevention organisations on pollution source identification using Bayesian probabilistic modelling. The group collaborates with Save the Elephants and Oxford University’s Zoology department on the impact of human footprint on animal behaviour in Kenya and with the Brazilian National Audit Office on tailings dam disaster prevention. Finally, the group works with Oxford University’s Earth Scientists and Bath University on global mapping of intra-continental seismic faults.
AREAS OF INTEREST
Machine learning; Bayesian Learning; Deep Learning; Satellite Imagery Data Analytics; Disaster Management; Environmental Protection.
RESEARCH GROUPS AND COLLABORATIONS
Machine Learning Research Group
PUBLICATIONS