Summary
My research involves the application of machine learning techniques towards the mapping and interpretation of urban health inequity, as part of the Pathways to Equitable Health in Cities (PEHC) project. PEHC is a global partnership of researchers, sponsored by the Wellcome Trust, aiming to improve population health and environmental sustainability by focusing on the causes of unequal outcomes for the welfare of inhabitants in cities and what may be done to tackle them.
My current work focuses on the use of imagery data (street view and satellite imagery) to investigate the fine scale spatial and temporal patterns of urban environmental features. I am currently focusing on Accra, Ghana. In order to add a layer of interpretability to widely used machine learning methods such as convolutional neural networks, my colleagues and I are working with object detection algorithms and class activation maps to highlight high level features of an environment which are either correlated or causally linked with health outcomes in cities.
I am also a keen science communicator, having been a contributor to Quantum Diaries and co-producing a radio show on nuclear physics for the Naked Scientists on BBC Cambridgeshire. More recently, I have written scripts for several videos of the popular YouTube series SciShow and co-wrote the PBS Digital series Crash Course Engineering, an educational show that covered a variety of engineering topics aimed at a broad audience. I have also hosted various outreach stalls at public events and given talks in schools. If you are interested in collaborating on/commissioning a scientific outreach project please be in touch.
My PhD was in High Energy Physics, studying the internal structure of the proton for applications at the Large Hadron Collider, at University College London. Prior to that, I obtained my Masters in Physics at the University of Oxford (2015).
Publications
Journals
Metzler AB, Nathvani R, Sharmanska V, et al., 2023, Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning, Science of the Total Environment, Vol:893, ISSN:0048-9697, Pages:1-14
Suel E, Muller E, Bennett J, et al., 2023, Do poverty and wealth look the same the world over? A comparative study of 12 cities from five high-income countries using street images, Epj Data Science, Vol:12, ISSN:2193-1127, Pages:1-14
Bennett J, Rashid T, Zolfaghari A, et al., 2023, Changes in life expectancy and house prices in London from 2002 to 2019: Hyper-resolution spatiotemporal analysis of death registration and real estate data, The Lancet Regional Health Europe, Vol:27, ISSN:2666-7762, Pages:1-13
Nathvani R, Clark S, Muller E, et al., 2022, Characterisation of urban environment and activity across space and time using street images and deep learning in Accra, Scientific Reports, Vol:12, ISSN:2045-2322
Clark S, Alli A, Nathvani R, et al., 2021, Space-time characterization of community noise and sound sources in Accra, Ghana, Scientific Reports, Vol:11, ISSN:2045-2322, Pages:1-14