Predicting geographic population density

A computer for predicting geographic population density, comprising:

• a non-transitory computer-readable storage medium storing executable computer program instructions comprising instructions for:
• defining a Markov Random Field (MRF) model for estimating a number of mobile devices used within a geographic area, wherein the MRF model represents a plurality of state variables xi as nodes in a regular 3-D lattice, wherein nodes in a plane of the lattice describe a plurality of corresponding geographic areas arranged in a grid, values of xi at the nodes in the plane indicate estimated numbers of mobile devices being used within the corresponding geographic areas at a time slice, and a third dimension of the lattice has nodes indicating values of xi at time slices preceding and following the time slice of the plane;
• applying current data describing a number of mobile devices currently observed within the geographic area and historical data describing a number of mobile devices historically observed within the geographic area to the MRF model to produce an estimate of a number of mobile devices currently being used within the geographic area;
• and
• predicting a population density for the geographic area responsive to the estimated number of mobile devices currently being used within the geographic area;
• and
• a processor for executing the computer program instructions.

A non-transitory computer-readable storage medium storing executable computer program instructions for predicting geographic population density, the instructions comprising instructions for:

• defining a Markov Random Field (MRF) model for estimating a number of mobile devices used within a geographic area, wherein the MRF model represents a plurality of state variables xi as nodes in a regular 3-D lattice, wherein nodes in a plane of the lattice describe a plurality of corresponding geographic areas arranged in a grid, values of xi at the nodes in the plane indicate estimated numbers of mobile devices being used within the corresponding geographic areas at a time slice, and a third dimension of the lattice has nodes indicating values of xi at time slices preceding and following the time slice of the plane;
• applying current data describing a number of mobile devices currently observed within the geographic area and historical data describing a number of mobile devices historically observed within the geographic area to the MRF model to produce an estimate of a number of mobile devices currently being used within the geographic area;
• and
• predicting a population density for the geographic area responsive to the estimated number of mobile devices currently being used within the geographic area.