Insights from Self-Organizing Maps for Predicting Accessibility Demand for Healthcare Infrastructure

Abstract

As urban populations grow worldwide, it becomes increasingly important to critically analyse accessibility—the ease with which residents can reach key places or opportunities. The combination of ‘big data’ and advances in computational techniques such as machine learning (ML) could be a boon for urban accessibility studies, yet their application in this field remains limited. In this study, we provided detailed predictions of healthcare accessibility across a rapidly growing city and related them to socio-economic factors using a combination of classical and modern data analysis methods. Using the City of Surrey (Canada) as a case study, we clustered high-resolution income data for 2016 and 2022 using principal component analysis (PCA) and a powerful ML clustering tool, the self-organising map (SOM). We then combined this with door-to-door travel times to hospitals and clinics, calculated using a simple open-source tool. Focusing our analysis on senior populations (65+ years), we found that higher income clusters are projected to become more prevalent across Surrey over our study period. Low income clusters have on average better accessibility to healthcare facilities than high income clusters in both 2016 and 2022. Population growth will be the biggest accessibility challenge in neighbourhoods with good existing access to healthcare, whereas income change (both positive and negative) will be most challenging in poorly connected neighbourhoods. A dual accessibility problem may arise in Surrey: first, large senior populations will reside in areas with access to numerous and close-by, clinics, putting pressure on existing facilities for specialised services. Second, lower-income seniors will increasingly reside in areas poorly connected to healthcare services, which may impact accessibility equity. We demonstrate that combining PCA and SOM clustering techniques results in novel insights for predicting accessibility at the neighbourhood level. This allows for robust planning policy recommendations to be drawn from large multivariate datasets.

A multi-dimensional digital twin use cases classification framework

“…Bartos and Kerkez (2020) included infrastructure along with natural environment, while others considered the interactions between infrastructure and socio-economic layers (Jadli & Hain, 2020;Wang et al, 2020;Barmpounakis & Geroliminis, 2020;Nallaperuma et al, 2019). Some authors alternatively involved varying combinations of three city layers while delivering DT purposes (Anejionu et al, 2019;Honarvar & Sami, 2019;Kourtit & Nijkamp, 2018;Francisco et al, 2020;Mavrokapnidis et al, 2021;Barkham et al, 2018;Mayaud et al, 2019), while others included all four as required within some other applications (Pettit et al, 2018;Yabe & Ukkusuri, 2019).…”

Assessing Global Environmental Sustainability Via an Unsupervised Clustering Framework

“…It is possible that a country has a low EPI rank, but is in one of the nodes that represent relatively better environmental performance. The SOM algorithm has been implemented in a variety of applications from ecological to urban systems [30][31][32][33][34][35]. However, the framework presented here is one of the first studies, to our knowledge, in which SOM has been implemented as part of a larger framework aimed at evaluating environmental sustainability, rather than simply being used to classify the evaluations of other indices.…”

Improving Feature Map Quality of SOM Based on Adjusting the Neighborhood Function

“…xt ðÞÀw c t ðÞ kk (5) where x(t) is the input sample at the training t; w c (t) is the BMU's weight vector of sample x(t); T is total of training times.…”

“…Among SOM's application areas, urban design is a potential area. Many of SOM's applications can be included in urban design such as: analysis of growth factors in urban design proposal [1], consider urban spatial structure [2], analysis of city systems [3], city data mining [4], predicting accessibility demand for healthcare infrastructure) [5], etc. However, for SOM's calculation results to be more accurate, improving the quality of feature map is a problem to solve.…”