Visualization for epidemiological modelling: challenges, solutions, reflections and recommendations

Abstract

We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs-a series of ideas, approaches and methods taken from existing visualization research and practice-deployed and developed to support modelling of the COVID-19 pandemic. Structured independent commentary on these efforts is synthesized through iterative reflection to develop: evidence of the effectiveness and value of visualization in this context; open problems upon which the research communities may focus; guidance for future activity of this type and recommendations to safeguard the achievements and promote, advance, secure and prepare for future collaborations of this kind. In describing and comparing a series of related projects that were undertaken in unprecedented conditions, our hope is that this unique report, and its rich interactive supplementary materials, will guide the scientific community in embracing visualization in its observation, analysis and modelling of data as well as in disseminating findings. Equally we hope to encourage the visualization community to engage with impactful science in addressing its emerging data challenges. If we are successful, this showcase of activity may stimulate mutually beneficial engagement between communities with complementary expertise to address problems of significance in epidemiology and beyond. See https://ramp-vis.github.io/RAMPVIS-PhilTransA-Supplement/. This article is part of the theme issue 'Technical challenges of modelling real-life epidemics and examples of overcoming these'.

Keywords: computational notebooks; epidemiological modelling; visual analytics; visual design; visualization.

Figure 1.

Six excerpts of an animation of a modelled disease transmission network [101] are visualized here using DynNoSlice [102,103]. Points are people, with connections showing infection pathways between them and revealing the fragmented nature of a modelled disease outbreak. The final image (right) shows detail, with a close up of the largest components in an infection network, with nodes colour-coded by infection state. Modellers responded to this visualization by lowering the random infection rates used in the modelling.

Figure 2.

Project architecture expressed using the Four Levels of Visualization [138] model. Structuring and planning our engagement in light of the model [98] helped us coordinate the SCRC volunteering effectively, efficiently and flexibly. By identifying needs for disseminative, observational, analytical and model developmental visualization we were able to identify six activities, and plan for the different amounts of effort needed for each. This enabled us to deploy the available VIS volunteers based on their expertise appropriate for each level of tasks and provide flexible visualization support across SCRC [138]: 729. We used the model to develop an iterative approach to establishing opportunities, supporting and developing needs, prototyping solutions and reflecting on action that underpins this paper.

Figure 3.

Nine excerpts (left) of an interactive exploration of a modelled disease outbreak visualized using our Gridded Glyphmap prototype [137]. Cells represent interactively defined areas in Scotland, with areas of higher populations being shown in more vibrant colours. Each glyph shows proportions of population in particular disease states (colours, horizontal proportions) in 10-year age bands (vertical rows), revealing the spatial and age-based characteristics of a modelled disease outbreak. The large image (right) shows a wider spatial overview of a single time-point at a particular scale. Modellers interacted with the output data to reveal patterns that resulted in changes to the model code and deeper understanding of the effects of modification to the model as knowledge of the disease progressed.

Figure 4.

We developed an effective means of generating thousands of viable online interactive visualizations and hundreds of dashboards by developing a means of Propagating Visual Designs from the SCRC data streams [115]. This semi-automated process maps single or multiple datasets to particular visual forms (plot types). Our application also supports quality assurance over the propagation process, to ensure the propagated visual designs are reasonable. The approach uses an ontology [131] to facilitate propagation by formally representing the relationship between dataset and visual device. This provides both flexibility and generalization as the mappings are determined by the ontology, which is established by human experts. The process provides a good example of the kind of human in the loop decision-making that visualization can support, resulting in down-stream efficiencies in this instance by encoding expertise that can be propagated and thus making good use of expert time. Here, visual analysis supports efficient and effective visualization design as we search for appropriate design solutions for observational visualization [138]:729.