CHENNAI: The Chennai Unified Metropolitan Transport Authority (CUMTA) is set to map travel demand around all 41 operational Phase-I Metro stations, catering to nearly 3.5 lakh passengers daily, using anonymised mobile and GPS data.

The exercise is expected to give them a granular picture of travel demand around each station and help it plan first- and last-mile feeder services.

CUMTA has invited bids for a two-month consultancy to prepare big data-based origin-destination (OD) matrices for the catchment areas of the 41 stations. The study will define a 5 km road-distance influence area around each station and divide it into traffic analysis zones (TAZs) of approximately 0.5 sq km each.

“It is an effort to identify not only how existing Metro passengers travel but also wider movement that the Metro network is currently not capturing,” CUMTA special officer I Jeyakumar said, adding that, “A person travelling between the two locations may not necessarily use the Metro even though the network serves both ends. Understanding such movements would require anonymised mobility data beyond Metro ticketing records.”

The consultant will have to procure anonymised GPS traces from smartphone applications or mobile-network data covering at least three months, with representative coverage of around 1015% of the target population.

According to CUMTA, the data supplied to the authority would contain aggregated travel movements rather than individual movement histories. Machine learning-based trip-chaining algorithms will then be used to convert location pings into trips and dwell periods and classify them by origin, destination, peak or offpeak period and trip length.

The consultant will prepare separate OD matrices for average daily travel, a three-hour morning peak, a three-hour evening peak and a six-hour off-peak period. The tender requires the consultant to produce a web-based visualisation platform showing the study area, TAZs and OD movements through heatmaps and desire-line diagrams.

With regard to privacy concerns, CUMTA said individual-level data will not be supplied and that the information it receives will be anonymised/aggregated. “The data will be under our control,” he said. The consultant will also have to hand over the raw and final datasets, maps, GIS shapefiles and working files to CUMTA.