SAN FRANCISCO EMERGENCY CALLS

Generation of the last forecasts: 15 October 2025 07:54:22 (UTC)

ABOUT THIS PROJECT

Overview and discussion

This model predicts the probability of emergency medical calls to the San Francisco Fire Department (SFFD). It utilizes records from the SFFD and integrates them with atmospheric, calendar, and additional data to forecast the likelihood of calls within the next hour over a 7-day period. The predictions are visualized on Google Maps, color-coded from green (indicating low probabilities) to red (indicating high probabilities).


how to use it?

The map is initially displayed with the current prediction (at San Francisco local time) of the probabilities of calls for medical incidents and is automatically refreshed every hour. Use the timeline bar (below the map) or the time control panel (on the map) to get a forecast at any other available time.

You can also change the region by moving on the map, change the scale or the background settings.

The minimum and maximum values of the probabilities are initially displayed on the map. You can display the forecast at any other place by directly clicking on the map. Use the button "Remove all markers" to delete all the displayed probabilities.


.

How does it work?

This project uses the "Fire Department Calls for Service" dataset (see below for details). These calls for service counts are combined with calendar and weather data from various models. Artificial intelligence and machine learning techniques are then used to build predictive models and forecasts for future calls probabilities.


About the calls for service data source

All the data are provided by the San Francisco Fire Department and are available at this link under the Open Data Commons Public Domain Dedication and License.


Terms of use

All the data generated by this experimental model are freely available without warranty of any kind.