Location network analysis tool for predicting contamination change

A computer-implemented method for predicting contamination change, the computer-implemented method comprising:

• receiving geolocation information indicating aggregated locations of multiple mobile devices configured to move in a geographic area,
• wherein the multiple mobile devices are for a group of subscribers to one or more communication providers for the geographic area;
• and
• wherein the geolocation information comprises at least two measured locations for a given mobile device of the multiple mobile devices;
• generating a time series representing mobility network graphs over a first time period;
• wherein the time series is generated by, for each of respective subperiods of the time series, generating data representing estimated movement of one or more members of a population between an origin location and a destination location of multiple locations within the geographic area;
• and
• wherein the estimated movement is estimated based on the geolocation information and a total population for the geographic area;
• generating one or more metrics derived from the time series;
• determining contamination information indicating a respective contamination status for each location of the multiple locations for each of the respective subperiods of the time series;
• and
• generating a computer model to predict changes in the contamination information in a second time period subsequent to the first time period by:
• estimating one or more estimations of an inferred contamination status of the population at a given subperiod of the time series;
• and
• generating a set of correlations comprising a respective correlation between the contamination information and a respective metric of the one or more metrics derived from the time series.

A computing system for predicting contamination change, the computing system comprising processor and memory, the memory containing instructions executable by the processor wherein the computing system is configured to:

• receive geolocation information indicating aggregated locations of multiple mobile devices configured to move in a geographic area,
• wherein the multiple mobile devices are for a group of subscribers to one or more communication providers for the geographic area;
• and
• wherein the geolocation information comprises at least two measured locations for a given mobile device of the multiple mobile devices;
• generate a time series representing mobility network graphs over a first time period;
• wherein the time series is generated by, for each of respective subperiods of the time series, generating data representing estimated movement of one or more members of a population between an origin location and a destination location of multiple locations within the geographic area;
• and
• wherein the estimated movement is estimated based on the geolocation information and a total population for the geographic area;
• generate one or more metrics derived from the time series of the mobility network graphs;
• determine contamination information indicating a respective contamination status for each location of the multiple locations for each of the respective subperiods of the time series;
• and
• generate a computer model to predict changes in the contamination information in a second time period subsequent to the first time period by:
• estimating one or more estimations of an inferred contamination status of the population at a given subperiod of the time series;
• and
• generating a set of correlations comprising a respective correlation between the contamination information and a respective metric of the one or more metrics derived from the time series.