English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present an Extended Kalman Filter framework for system identification andcontrol of a stochastic high-dimensional epidemic model. The scale and severityof the COVID-19 emergency have highlighted the need for accurate forecasts ofthe state of the pandemic at a high resolution. Mechanistic compartmentalmodels are widely used to produce such forecasts and assist in the design ofcontrol and relief policies. Unfortunately, the scale and stochastic nature ofmany of these models often makes the estimation of their parameters difficult.With the goal of calibrating a high dimensional COVID-19 model using low-levelmobility data, we introduce a method for tractable maximum likelihoodestimation that combines tools from Bayesian inference with scalableoptimization techniques from machine learning. The proposed approach usesautomatic backward-differentiation to directly compute the gradient of thelikelihood of COVID-19 incidence and death data. The likelihood of theobservations is estimated recursively using an Extended Kalman Filter and canbe easily optimized using gradient-based methods to compute maximum likelihoodestimators. Our compartmental model is trained using GPS mobility data thatmeasures the mobility patterns of millions of mobile phones across the UnitedStates. We show that, after calibrating against incidence and deaths data fromthe city of Philadelphia, our model is able to produce an accurate 30-dayforecast of the evolution of the pandemic.

AutoEKF: Scalable System Identification for COVID-19 Forecasting from Large-Scale GPS Data