Replica produces large-scale models that accurately represent mobility, economic activity, people, and land use in detail throughout the United States.
Replica customers have access to a number of datasets, which are described below. Click to see detailed descriptions and schema.
Replica Places is a high-fidelity simulation that accurately represents the population and its travel patterns. Customers use Places data to improve planning and monitoring of transportation and land use systems, and to make decisions related to the ways people interact with the built environment.
Places is the world’s only calibrated travel demand model delivered at nationwide scale offered via software-as-a-service (SaaS). It is delivered in a pioneering privacy-sensitive approach.
The Places dataset is a complete trip and population table for a typical weekday and typical weekend day for the selected season and region. Places data is accessible through Replica’s web-based platform and through direct database access.
Replica Places megaregions cover geographies that include between 10 million and 50 million residents. Each data table is cross-tabular, meaning it is linked to other tables through common IDs, including person_id (the person making the trip), activity_id (the trip), or route_id (transit routes or network links used for a trip).
Data can be filtered on any single attribute or combination of attributes. Each row of data in the simulation output reflects a single trip, with characteristics about the trip (e.g., origin, destination, mode, purpose, routing, duration) and trip taker (e.g., age, race/ethnicity, income, home location, work/school location).
The Places trip table contains the unique records and associated attributes for the trips between origin and destination points. Trip data represents the modeled output for a typical Thursday or Saturday during a three-month Replica season.
A randomly assigned unique identifier defined for each trip. A trip is defined as travel between two locations with a discrete purpose at the origin and destination. Some intermediate stops with short dwell time may be captured within a single trip. Criteria for this dwell time may vary. Examples:
A randomly assigned unique identifier for each person modeled within the synthetic population.
A randomly assigned unique identifier for each household modeled within the synthetic population.
The primary transportation mode used for the trip.
A trip is often made up of multiple travel modes, such as a journey to work that includes a walk to a rail station followed by a subway ride. In this case two modes were used by the traveler during their trip, walking and public transit. Only the primary mode of travel across a set of trip segments is included.
The primary mode is determined using the following ranking: 1) Public transit, 2) Driving (private auto)/Auto passenger/Taxi/TNC, 3) Biking, 4) Walking.
Valid values are:
The destination activity assigned to a synthetic person. For example, if a person is traveling to work, the purpose of the trip is ‘Work,’ whereas if a person is traveling to a restaurant the activity is ‘Eat.’
Valid values are:
Indicates what type of tour that included this trip. Tours are travel events that start at one location and return to that same location. For example, when a person travels to work and returns home, this a home-based work tour. A tour can have two or more trips.
Valid options are:
The activity assigned to a synthetic person prior to starting travel.
Valid values are:
Timezone of the trip’s start location, using standard tz naming conventions.
Date and 24-hour time of trip start, reported as yyyy-mm-dd hh:mm:ss timezone.
Hour of day that the trip started, reported in the local time zone in 24-hour time format. Values in this field range between 0 and 23.
Date and 24-hour time of trip end, reported as yyyy-mm-dd hh:mm:ss timezone
Hour of day that the trip ended, reported in the local time zone in 24-hour time format. Values in this field range between 0 and 23.
Duration of trip in minutes, calculated as the difference between the trip start_time and end_time.
Distance in miles measured along the trip route.
The ID of the transit route used for a trip. Only applies to trips with mode as “PUBLIC_TRANSIT.”Transit Agency name and Route ID from agency’s GTFS feed.
Unique ID assigned to the link (road segment) that the trip is associated with.
The vehicle type assigned to the vehicle of the synthetic trip.
Valid values are:
• PASSENGER_CAR
• MEDIUM_COMMERCIAL: Medium-duty commercial vehicles (14,000 – 26,000 lbs)
• HEAVY_ COMMERCIAL: Heavy-duty commercial vehicles (>26,000 lbs)
• MOTORCYCLE
Note: If values are NULL, this means that this data is not available for the region yet but we hope to have it soon.
The fuel type assigned to the vehicle of the synthetic trip.
Valid values are:
Note: If values are NULL, this means that this data is not available for the region yet but we hope to have it soon.
The fuel technology assigned to the vehicle of the synthetic trip.
Valid values are:
Note: If values are NULL, this means that this data is not available for the region yet but we hope to have it soon.
The US Census Bureau-assigned FIPS code of the block group from which the trip originated.
Latitude of the geometric centroid for the origin block group, reported in decimal degrees, WGS 84
Longitude of the geometric centroid for the origin block group, reported in decimal degrees, WGS 84.
US Census Bureau-assigned FIPS of the block group in which the trip ended.
Latitude of the geometric centroid for the destination block group, reported in decimal degrees, WGS 84.
Longitude of the geometric centroid for the destination block group, reported in decimal degrees, WGS 84.
The primary land use category of the trip origin.
Valid values are:
The secondary land use category of the trip origin.
Valid values are:
• single_family
• multi_family
• office
• retail
• non_retail_attraction
• education
• healthcare
• military
• civic_institutional
• transportation_utilities
• open_space
• agriculture
• other
• unknown
The primary land use category of the trip destination.
Valid values are:
The secondary building use category of the trip destination.
Valid values are:
The primary building use category of the trip origin.
Valid values are:
The secondary building use category of the trip origin.
Valid values are:
• single_family
• multi_family
• office
• retail
• non_retail_attraction
• education
• healthcare
• military
• civic_institutional
• transportation_utilities
• open_space
• agriculture
• other
• unknown
The primary building use category of the trip destination.
Valid values are:
The secondary building use category of the trip destination.
Valid values are:
• single_family
• multi_family
• office
• retail
• non_retail_attraction
• education
• healthcare
• military
• civic_institutional
• transportation_utilities
• open_space
• agriculture
• other
• unknown
The Places population table contains records for each person modeled within the synthetic population produced by Replica. Each record includes a set of attributes describing the person’s demographic and socioeconomic characteristics and the block-group assignment for their work, home, and school locations.
Population data represents the modeled output for each three-month Replica season.
Model inputs include the following products from the U.S. Census Bureau: American Community Survey 5-year estimates, TIGER/Line data, LEHD Origin-Destination Employment Statistics Data, and ACS Public Use Microdata Sample (PUMS), the Census Transportation Planning Products Program (CTPP) as well as data from the National Center for Education Statistics, US Department of Education, building data and proprietary parcel data and points of interest data.
Unique identifier of a household.
Unique identifier of a person.
The US Census Bureau-assigned FIPS code of the census block group containing the housing unit based on the decennial census 2010.
The US Census Bureau-assigned FIPS code of the census block group containing the person’s workplace (for employed persons only).
The US Census Bureau-assigned FIPS code of the census block group containing the person’s school (for students only).
The US Census Bureau-assigned FIPS code of the census tract containing the housing unit.
The US Census Bureau-assigned FIPS code of the census tract containing the person’s workplace (for employed persons only).
The US Census Bureau-assigned FIPS code of the census tract containing the person’s school (for students only).
Age range a person falls within.Value ranges include:
Age, in years old, assigned to the person.
Sex assigned to the person, male (M) or female (F).
Race assigned to the person.
Valid values include:
Ethnicity of a person.
Valid values include:
• not_hispanic_or_latino
• hispanic_or_latino
Range a person’s annual income falls within.
Value ranges include:
Total annual income of a person.
Employment status of a person.Valid values include:• employed• notinlf• under_16• unemployed
Education level of a person.
Valid values include:
• advanced_degree
• bachelors_degree
• high_school
• k_12
• no_school
• some_college
• under_3
Current grade level assigned to a person.
Valid values include:
• graduate
• kindergarten
• not_attending_school
• school
• undergraduate
Industry sector a person works within, reported in NAICS code. For a list of NAICS codes see:
Search NAICS Codes by Industry
The role of the person in the household.
Valid values include:
Number assigned to the subfamily that the person belongs to in a household.
Relationship of a person within the subfamily.
Valid values include:
• child
• husband/wife_no_children
• husband/wife_with_children
• parent_with_child
• N/A
Typical commute mode used by a person.
Valid values include:
Tenure of household.
Valid values include:
Indicates mobility status (if the household has lived in the same unit 1 year ago).
Valid values include:
Income range that the total income of the household falls within.
Valid values include:
Income range that the total income of the household falls within.
Valid values include:
Total income of the household.
Household family structure.
Valid values include:
• family_single
• GQ
• living_alone
• married_couple
• nonfamily_single
Number of vehicles owned by a household.
Valid values include:
Indicates the unit in the household’s structure.
Valid values include:
Indicates whether or not the person is a resident of the region.
Valid values include:
Indicates the household language.
Valid values include:
Latitude of the block group centroid representing the home location, reported in decimal degrees, WGS 84.
Longitude of the block group centroid representing the home location, reported in decimal degrees, WGS 84.
Latitude of the block group centroid representing the work location, reported in decimal degrees, WGS 84 (for employed persons only).
Longitude of the block group centroid representing the work location, reported in decimal degrees, WGS 84 (for employed persons only).
Latitude of the block group centroid representing the school location, reported in decimal degrees, WGS 84 (for students only).
Longitude of the block group centroid representing the school location, reported in decimal degrees, WGS 84 (for students only).
The Places network volumes table contains total estimated trip counts by mode for each network link within a given region. The trip counts represent the amount of traffic across the link on a typical Thursday during the given Replica season.
Network links (or, edges) are the streets or pathways upon which vehicles or people can travel. A single street is typically split into multiple segments, with the split points set at street intersections. Two way streets are modeled with separate network links, one for each direction of travel.
Arterial network links include freeways, highways, primary, secondary, and tertiary segments. The functional classification defined for the segments (freeways, highways, primary, secondary, and tertiary) are derived from OpenStreetMap street data. Most residential streets and service lanes are excluded from this dataset.
A unique identifier for the network link.
The latitude of the starting point of the network link, stored in decimal degrees.
The longitude of the starting point of the network link, stored in decimal degrees.
The latitude of the end point of the network link, stored in decimal degrees.
The longitude of the starting point of the network link, stored in decimal degrees.
The common name of the network link if available. Matches the name assigned by OpenStreetMap.
The classification of the link based on OpenStreetMap data.
Total estimated trip counts on network link within the selected region.
The Places land use table contains a nationwide snapshot of aggregated parcels, their land use, their total built square footage, and their dwelling unit count for the Fall 2021 season. Please note that the built square footage is a modeled representation of total three-dimensional building space. There could be multiple buildings per parcel.
A randomly assigned unique identifier defined for each trip. A trip is defined as travel between two locations with a discrete purpose at the origin and destination. Some intermediate stops with short dwell time may be captured within a single trip. Criteria for this dwell time may vary. Examples:
The name of the corresponding row’s geography, as defined by the US Census Bureau or specified by the user for custom geography uploads.
The number of dwelling units in the corresponding row’s geography, assigned to single_family, multi_family, or mixed_use buildings.
The total area for all parcels in your selected geographies in square feet.
The total parcel area for each land use, in square feet.
Mixed-use parcels are assigned to their estimated primary use.
Primary land use categories are:
The total area for all buildings in your selected geographies in square feet.
The total building area for each building use, in square feet. There are no mixed-use fields – mixed-use buildings have their built area split across all estimated uses.
Building use categories are:
• residential single family
• residential multifamily
• commercial retail
• commercial office
• commercial non-retail attraction
• industrial
• civic healthcare
• civic education
• civic other
• transportation utilities
• open space
• agriculture
• other
• unknown
With Replica, public agencies leverage valuable data and insights to support grant funding applications. Federal grant applications almost always require information on equity and existing conditions. WIth Replica data, this insight is easily accessible.
Replica data has been used to:
3610 W. 95th Street
Leawood, KS. 66206