Projects / AI Innovation Challenge

Classifying Rooftops Through Neural Networks to Eliminate Energy Waste of Facilities

Project completed! Results attached!

Omdena Featured image

The challenge partner is a Techstars Energy tech startup with the mission to provide a digital map of the largest commercial and industrial energy users in North America.

In this two-month Omdena Challenge, 50 AI changemakers collaborated to build AI solutions, which can help to significantly improve energy efficiency and sustainability of facilities. 

The Problem 

Access to customer electricity data is extremely important for society and energy companies who are looking to prioritize efficiency, sustainability, and make operational decisions about facilities (think solar, energy retrofit, and energy consulting companies). It allows them to understand how these facilities consume power, and where the best opportunities exist. However, electricity data is difficult to obtain and often requires significant engagement with the end-user to understand if they are qualified. 

This lag in time is inefficient and slows down go-to-market teams and efficient society impact. The Partner Platform allows users (energy sales teams) to easily search any territory, and view Energy Assessments of the covered facilities right away. The Energy Assessments include the estimated kilowatt-hour consumption for each of the 250,000 facilities that the platform covers. The Platform engages in predictive analytics to build these estimations and help energy sales teams go to the needy market quickly and effectively. One indicator of energy consumption could be rooftop type and rooftop equipment.

The Project Outcomes

The AI solution built has the intent to gain a better understanding of the energy intensity of a facility by assessing rooftop characteristics. The models classify rooftops into types, using a convolutional neural network (“CNN”) and Edge Detection. With the access to rooftop images for over 200,000 facilities across the US (soon to be Canada, Europe, and Asia). These images were classified into 1 of 5 categories:

  • Flat and Clear
  • Flat and Cluttered
  • Light Industrial
  • Heavy Industrial
  • Existing Solar

The project partner provided image examples of each category to help train the CNN. In short “cluttered” (see point 2) is a reflection of rooftop equipment such as HVAC systems. “Industrial” is a characteristic of the roof which tends to have more cylindrical or rectangular-shaped equipment. Existing solar would classify rooftops that already have solar panels installed. 

Even generating more classifications, and that there are more facility types that the partner hasn’t thought of. 

Below is some initial research on how edge detection might be helpful in building this AI:

Edge Detection Neural Net

This may be able to help distinguish industrially complex rooftops from simple or flat ones. Below is a screenshot from Google Maps which compares two facilities somewhere in Texas. You will get the code for this in an HTML file.

edge detection for rooftops using neural nets

First Omdena Project?

Join the Omdena community to make a real-world impact and develop your career

Build a global network and get mentoring support

Earn money through paid gigs and access many more opportunities

Your benefits

Address a significant real-world problem with your skills

Get hired at top companies by building your Omdena project portfolio (via certificates, references, etc.)

Access paid projects, speaking gigs, and writing opportunities


Good English

A good/very good grasp in computer science and/or mathematics

Student, (aspiring) data scientist, (senior) ML engineer, data engineer, or domain expert (no need for AI expertise)

Programming experience with C/C++, C#, Java, Python, Javascript or similar

Understanding of Computer Vision, Machine Learning, and/ or Remote Sensing

Application Form
media card
AI-Driven Temperature Analysis for Educational Environments in Tanzania
media card
CanopyWatch - Enhancing Deforestation Monitoring and Conservation in the Congo Basin using Machine Learning
media card
Streamline the Identification of Suitable Sites for Solar Panel Installations in UK

Become an Omdena Collaborator

media card
Visit the Omdena Collaborator Dashboard Learn More