Figures & data
Figure 1. SIRVC model: susceptible-infectious-recovered with vaccinations and inter-community interactions. An additional term moves susceptible individuals into the infectious group through interactions with external communities.
![Figure 1. SIRVC model: susceptible-infectious-recovered with vaccinations and inter-community interactions. An additional term moves susceptible individuals into the infectious group through interactions with external communities.](/cms/asset/e259e57b-eab1-4b78-9669-6e2f82c973bc/uaai_a_2055989_f0001_oc.jpg)
Table 1. Nomenclature.
Figure 3. Layered ensemble architecture for multi-scale pandemic prediction ranging from country through global level.
![Figure 3. Layered ensemble architecture for multi-scale pandemic prediction ranging from country through global level.](/cms/asset/306e76e2-6c80-46f8-8324-faf7bce84b8b/uaai_a_2055989_f0003_oc.jpg)
Table 2. Country-level GAT structure.
Figure 7. United States GAT model: final graph layer attention visualization. Edge color corresponds to min-max normalized edge attention.
![Figure 7. United States GAT model: final graph layer attention visualization. Edge color corresponds to min-max normalized edge attention.](/cms/asset/9a60627b-943c-44b7-b856-68178b157203/uaai_a_2055989_f0007_oc.jpg)
Table 3. Performance comparison for country-level model variations.
Figure 9. Middle ensemble layer predictions (Algorithm 2): Continent MLP trained with country SIRVC-GAT prediction: (a) Africa; (b) Asia; (c) Europe; (d) North America; (e) Oceania; (f) South America.
![Figure 9. Middle ensemble layer predictions (Algorithm 2): Continent MLP trained with country SIRVC-GAT prediction: (a) Africa; (b) Asia; (c) Europe; (d) North America; (e) Oceania; (f) South America.](/cms/asset/aeebbe98-1680-4f55-9533-9c1951d28130/uaai_a_2055989_f0009_oc.jpg)
Figure 10. Final ensemble layer prediction: World MLP trained with continent MLP prediction (proposed ensemble model described by Algorithm 2) compared to 1) using randomized country grouping in the middle layer and 2) training without a middle/continent layer.
![Figure 10. Final ensemble layer prediction: World MLP trained with continent MLP prediction (proposed ensemble model described by Algorithm 2) compared to 1) using randomized country grouping in the middle layer and 2) training without a middle/continent layer.](/cms/asset/7d8a03cb-b556-4d2b-90d1-6055e731e525/uaai_a_2055989_f0010_oc.jpg)
Table 4. Performance comparison for proposed layered ensemble (Algorithm 2) against baselines.