MyHEAT — Technology

Technology Overview

HEAT Maps use machine learning to create powerful, city-wide visualizations that show areas of energy loss in buildings.

Let us show you how -

How does it work?

MyHEAT delivers aerial thermal infrared imagery across entire cities. High resolution thermal infrared (TIR) imagery is collected quickly and economically, and then transformed using our innovative technology utilizing machine learning techniques to derive unique insight on the thermal efficiencies of every building in a city.

For our thermal data collection, MyHEAT builds on a world-class TIR sensor that integrates key benefits of traditional wide-area format digital cameras giving industry leading data fidelity and acquisition capabilities over traditional airborne cameras.

Once the thermal data is collected for a city, it is then transformed using our proprietary machine learning techniques to reveal building heat loss, and comparable efficiency metrics for the entire city. MyHEAT’s pipeline includes the ability to automatically correct for local factors. This means all buildings are evaluated as if they were collected at a single instance in time, allowing heat loss to be compared over different dates as well as between homes, neighbourhoods, and cities. The result is the creation of unique HEAT Maps and HEAT Ratings for all buildings across the entire city.

Sample HEAT Loss Map

HEAT Maps show potential heat loss areas from a bird’s-eye view. The thermal images indicate hot spots, or heat loss, in red and cooler areas in blue.

Sample HEAT Rating

HEAT Ratings offer a relative measure of how much heat a building is losing compared to similar buildings in the neighborhood and city.


Rahman, M.M., Hay, G.J., Couloigner, I., Hemachandran, B., and Bailin, J. 2015. A Comparison of Four Relative Radiometric Normalization (RRN) Techniques for Mosaicking H-Res Multi-Temporal Thermal Infrared (TIR) Flightlines of a Complex Urban Scene (PHOTO-D-14-00266). The ISPRS Journal of Photogrammetry and Remote Sensing, pp. 41.

Rahman, M.M., Hay, G.J., Couloigner, I., Hemachandran, B., and Bailin, J. 2014. An Assessment of Polynomial Regression Techniques for the Relative Radiometric normalization (RRN) of High Resolution Multi-Temporal Airborne Thermal Infrared (TIR) Imagery. Remote Sensing Special Issue (ISSN 2072-4292): Recent Advances in Thermal Infrared Remote Sensing Remote Sens. 2014, 6(12), 11810-11828; doi:10.3390/rs61211810.

Rahman, M.M., Hay, G.J., Couloigner I., and Hemachandran, B. Transforming image-objects into multiscale fields: A GEOBIA Approach to Mitigate Urban Microclimatic Variability within H-Res Thermal Infrared Airborne Flight-Lines. Remote Sens. 2014, 6, 9435-9457.

Abdulkarim, B., Kamberov, R., and Hay, G.J. 2014. Supporting Urban Energy Efficiency with Volunteered Roof Information and the Google Maps API. Remote Sens. 6, no. 10: 9691-9711.

Rahman, M.M, Hay, G.J., Couloigner, I., Hemachandran, B., Bailin, J., Zhang, Y., and Tam, A. 2013. Geographic Object-Based Mosaicing (OBM) of High-Resolution Thermal Airborne Imagery (TABI-1800) to Improve the Interpretation of Urban Image-Objects. IEEE Geoscience and Remote Sensing Letters – (GEOBIA 2012 Special Issue) Vol 10, NO. 4, July. 918-922.

Hay G.J., Kyle, C., Hemachandran, B., Chen, G., Rahman, M.M., Fung, T.S., and Arvai, J.L. 2011. Geospatial Technologies to Improve Urban Energy Efficiency. Remote Sens. 3, no. 7: 1380-1405.

Energy Made Visible