2026-10-11T10:57:49Z
https://api.figshare.com/v2/oai
oai:figshare.com:article/34035848
2026-09-30T17:41:53Z
category_1
category_15
category_21
category_734
category_931
category_132
portal_5
item_type_1
month_year_09_2026
<p>Robustness to mask design.</p>
Joseph Lemaitre (25145381)
Justin Lessler (116180)
Biophysics
Neuroscience
Biotechnology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Infectious Diseases
somewhat overconfident projections
leading ensemble methods
cdc flusight challenges
capture multimodal uncertainty
achieves forecast accuracy
2024 &# 8211
2022 &# 8211
influpaint generates realistic
encoding influenza seasons
provide important information
generative diffusion models
diverse epidemic trajectories
diffusion models
influpaint learns
influenza dynamics
simulated trajectories
epidemic dynamics
time evaluation
spatiotemporal images
rich distribution
retrospective evaluation
partial observations
hybrid dataset
highly accurate
flexible framework
emergent trends
disease dynamics
current mechanistic
conditional generation
best performance
<p>Black curves show observed hospitalizations during the 2023–2024 season; colored fans and lines show Influpaint predictive quantiles and medians. Insets show the conditioning mask for each panel, where green values are observed and red values are hidden and reconstructed by Influpaint. The arrow in each inset indicates which state/row is shown in the graph. <b>a.1–3.</b> Half-subpopulation spatial mask for California (a.1), Florida (a.2), and Maryland (a.3). <b>b.</b> Leave-one-state-out mask for North Carolina. <b>c.</b> Leave-one-state-out mask for Illinois. <b>d.</b> Midseason gap mask for Maryland. <b>e.</b> Reconstruction of the early-season dynamics conditioned on later-season observations for Florida. <b>f.</b> Checkerboard spatiotemporal mask for California.</p>
2026-09-30T18:00:00Z
Image
Figure
10.1371/journal.pcbi.1014846.g004
https://figshare.com/articles/figure/_p_Robustness_to_mask_design_p_/34035848
CC BY 4.0