Inferring land use from mobile phone activity

TL;DR

This paper demonstrates how mobile phone activity data can be used to infer land use patterns in urban areas, providing a cost-effective alternative to traditional survey methods.

Contribution

It introduces a machine learning approach to classify land use based on mobile phone activity, revealing dynamic population patterns and their relationship to land zoning.

Findings

Mobile phone data accurately identifies land use types.

Patterns of population movement correlate with land zoning.

Mobile data complements traditional land use information.

Abstract

Understanding the spatiotemporal distribution of people within a city is crucial to many planning applications. Obtaining data to create required knowledge, currently involves costly survey methods. At the same time ubiquitous mobile sensors from personal GPS devices to mobile phones are collecting massive amounts of data on urban systems. The locations, communications, and activities of millions of people are recorded and stored by new information technologies. This work utilizes novel dynamic data, generated by mobile phone users, to measure spatiotemporal changes in population. In the process, we identify the relationship between land use and dynamic population over the course of a typical week. A machine learning classification algorithm is used to identify clusters of locations with similar zoned uses and mobile phone activity patterns. It is shown that the mobile phone data is capable of delivering useful information on actual land use that supplements zoning regulations.