In collaboration with his Institute of Health Harvard, the Google released today the public forecasts for him COVID-19, a set of models that provide case studies of COVID-19, deaths, ICU usage, ventilator availability and other measurements for the next 14 days for US states.
The models are trained in public data, such as those of Johns Hopkins University, Descartes Labs and the United States Census Bureau, and the Google states that they will continue to be informed under the guidance of its associates at Harvard.
They enable targeted trials and interventions in public health from county to county, theoretically enhancing the ability of data users to respond to its rapidly evolving pandemic COVID-19.
For example, healthcare providers could integrate the intended number of cases as a point of reference in their resource planning, staffing and service scheduling.
Meanwhile, state and county agencies could use infection forecasting to conduct strategic tests to identify areas at risk.
To create public forecasts for him COVID-19, the Google reports that its researchers have developed a new time series machine learning approach that combines AI with an intelligent epidemiological base.
From their design, the models are trained in public data and utilize an architecture that allows researchers to find relationships they have identified (the models) to interpret them because they make specific predictions.
They are also scheduled to secure forecasts for countries hardest hit by it COVID-19, for there is a higher success rate, due to the larger number of data.