Exploring how affordable, global people-centred geospatial data products could help planners to evaluate, plan and track progress to UN SDGs 3, 11 and 15

More and more geospatial information on environmental quality is becoming available. This emerging data has numerous applications including enabling sustainable and healthy city planning, encouraging citizen awareness and healthier behaviours as well as tracking progress towards healthy and sustainable outcomes. However, the production of these datasets is expensive and resource intensive and planners are not used to dealing with large GIS datasets. This significantly limits the realisation of the UN Sustainable Development Goals 11 (Sustainable Cities and Communities), 3 (Good Health and Wellbeing) and 15 (Life on Land). Cities without such environmental datasets are therefore limited in their ability to effectively justify, plan and track progress of significant urban interventions and citizen behaviour change.

Tranquil City has prototyped an innovative, people-centred and cost-effective geospatial data product package that delivers strategic and high-resolution environmental quality and infrastructure information to promote healthier behaviours through tech platforms. Our method uses machine learning (ML) techniques to learn from 'data rich' cities and train a model to use globally available datasets to predict high-resolution data for many environmental factors (air quality, noise, green space quality, water elements, tree cover, Tranquillity and Healthy Streets Indices) in any city or area worldwide at a fraction of the cost of the standard modelling approaches used to date. This data is commercialised via our licensed data toolkits and APIs for access integration into public-facing applications that can encourage healthier, more sustainable behaviours.

Our plan for the future is to support planning authorities and practitioners to work toward the SDGs. With Innovate UK's funding, we will engage with current clients and stakeholders to understand and iterate on our initial concepts of offering this data for spatial planning, including validation, scaling and delivery. The outputs will include feasibility studies of how planners would most like to use and handle the data, model and monitor the impact of interventions against SDG targets and how best to implement wide-scale data production methods.