Sizztech has designed the Forecaz Modeller, an automated modelling tool that allows organisations to reliably perform urban growth forecasting and generate demand models for the variety of infrastructure networks they manage. Forecaz Modeller utilises a first principles methodology to derive the residential and non-residential planning assumptions from lot level demographics.The modeller employs Bayesian Network probabilistic graphical models to perform predictive development growth sequencing. Utilising government population growth projections to control the urban growth targets, the modeller allocates and sequences land parcels to their highest and best land use.

Forecaz Modeller provides an interactive user interface that gives end users the ability geospatially view and total the demand growth and demographics by spatial areas. Examples include: Statistical Local Areas, Suburbs and Service Area Catchments. The modeller allows for different scenarios to be defined, with different growth parameters that can be used for “what-if” analysis. Utilising advanced spatial services, users can compare forecast models and visually determine the locations where large variances are occurring with the results clustered into “bubble maps”.

Spatially compare forecast growth models

Forecaz Modeller’s benefits include:

  • A geospatial modelling tool that automates the calculation of planning and infrastructure network demand assumptions and infrastructure charges revenue using a consistent and repeatable methodology.
  • Allows organisations to build and maintain dynamic urban growth and network demand models for today and into the future. This removes the requirement to engage external consultants at regular intervals to review and update these models.
  • The ability to define multiple infrastructure networks (such as Water Supply, Sewerage, Stormwater) for incorporation into forecast models.
  • Provides the facility to copy and refine various scenario forecast models with independent model parameters and planning assumptions. The modeller allows different scenarios to be spatially compared and analysed against each other.
  • Allow a baseline year and one or more projection years to be generated that forecasts the assumed growth in a land parcel’s demographic data and calculates the infrastructure network demand at each projection year.
  • Able to calculate the forecast infrastructure charges revenue for the assumed demand growth, supporting both a service area based charging methodology and a land use based charge methodology for these calculations.
  • Provides a spatial viewer and reporting tool that allows visualisation of the aggregation of the demand forecasts by spatial areas, such as Statistical Local Areas, Infrastructure Network Services Areas, and Suburbs.
  • Provides the ability to search for land parcels utilising address or lot/plan. Users can view the forecast attributes of those land parcels including: demographics, network demand, infrastructure charges or future water consumption.
  • Allows users to search for Development Applications and compare the assumed network demand for land parcels subject to a Development Application against the actual demand generated by the Development Application.
  • Accounts for transient workers/populations in the forecast model’s projections.
  • Provides a function to export sequenced demand as geospatial XY centroid data that can be used by infrastructure network modelling tools.

View lot level demographic assumptions

Forecaz Modeller is a tool that allows significant improvements in the conversion of planning assumptions into demand forecasts. By automating and providing a repeatable and reliable forecasting process, the modeller significantly improves the detail and quality of development growth forecasts and assumptions. These forecasts provide financial confidence, allowing the balancing of the funding of the future capital works programme against verified and tested forecast growth models. Utilising Forecaz Modeller allows organisations to achieve significant savings in staff time and while providing confidence that repeatable and predictable growth projections are being generated. In many cases achieving a return on investment inside 12 months.