The classification and analysis of regional building stock characteristics using GIS

Sponsor: EPSRC
Name: Phillip Jones
Start Date: 01/02/2007

The EEP model is a practical computer based modelling framework that quantifies energy use and associated emissions for cities to help plan to reduce carbon dioxide. This model has be used to demonstrate how considerable financial, energy, and carbon savings can be made through the targeting of energy efficiency measures appropriate to certain house types. Regional energy models, such as EEP, require an accurate description of the built characteristics of an area. Although surveys provide a level of information that was otherwise unobtainable, the investment in manpower and time on a city/regional scale has proved to be a barrier to the further uptake of the model.

This project applies a new method of pattern recognition algorithms to analyse digital maps develop techniques in order to classify individual dwellings within an area. At a larger urban level the use of pattern recognition has been established, using OS maps to infer urban land use. This has successfully identified areas with similar built ages by considering street layout patterns. However in order to achieve the level of detail necessary for individual property level analysis, data at an individual dwelling level is required.