Covid-19 Projections are generated using a compartmental model that simulates Covid-19 transmission in each state and the US using a humidity-driven SEIRS dynamics. Model variables and parameters are sequentially updated each week using the ensemble adjustment Kalman filter and new observations.
Model inputs are state and national-level weekly confirmed Covid-19 hospital admissions from the HHS Covid-19 hospitalization data set, and seasonal absolute humidity data from the North America Land Data Assimilation System (NLDAS).
Influenza forecasts are made using an inverse-WIS weighted ensemble of several component models - an SEIRS compartmental model with EAKF, an ARIMA model, a random walk with drift, and the N-HiTS and N-BEATS deep-learning models.
The dynamical model simulates influenza transmission in each state and the US using a humidity-driven SEIRS dynamics. Model variables and parameters are sequentially updated each week using the ensemble adjustment Kalman filter and new observations. Forecasts are generated by integrating the optimized model into the future. Autoregressive Integrated Moving Average model and baseline models use implementations available in the fable R package (ARIMA and RW, respectively). We employ multivariate versions of N-HiTS and N-BEATS models as implemented in the darts python package, trained on modified state-level ILI data and hospitalization data. To build ensemble, the quantile distributions of the component models are weighted by the sum of inverse-WIS scores, over last 4 weeks. The 4-week window is target and location-specific and are recomputed at each forecast week.
Model inputs include state and national-level daily confirmed influenza hospital admissions, queried using covidcast R package; State and national-level ILINet surveillance data, queried using cdcfluview R package; and seasonal absolute humidity data from the North America Land Data Assimilation System (NLDAS).
In development
Visualizations of these short-term projections will soon be available online
For more information, contact Dr Sen Pei sp3449@cumc.columbia.edu
Covid-19 Model: Teresa Yamana, Sen Pei
Influenza Model: Rami Yaari, Teresa Yamana, Sen Pei, Jeffrey Shaman
Visualizations: Tonguc Yaman