DECODER
DECODER is an integrated research initiative focused on enabling data-driven decarbonization across building portfolios. The project is developing a cognitive digital twin platform that supports building owners, operators, and decision makers in planning, assessing, and monitoring retrofit and commissioning strategies.
The DECODER platform is designed to ingest and process building data to generate actionable insights at both the building and portfolio level. It supports more informed decisions on energy use, retrofit prioritization, and operational performance.
DECODER is particularly relevant for:
- Real estate owners seeking to reduce emissions and improve building performance across portfolios
- Policy-makers and public sector leaders looking to support evidence-based retrofit strategies and decarbonization at scale
DECODER is a funded IMPACT project, supported for its focus on large-scale technological innovation. Based at Concordia University, Volt-Age is funded by the Canada First Research Excellence Fund and is the number one electrification research program in the country.
DECODER brings together a set of interconnected research areas that support the development of intelligent, data-driven building systems including:
- Data modeling and integration for building decarbonization processes
- Cognitive digital twin development
- Smart and ongoing commissioning
- Building energy modeling and optimization
- Fault detection and resolution
- Portfolio prioritization
- Retrofit design and optimization
These areas collectively enable a shift from reactive building management to proactive, data-informed decision making.
DECODER comprises five concurrent and interconnected sub-projects (also called 鈥淲ork Packages鈥�) that collectively support the development of the platform and its real-world application.
Work Package 1: Use case definitions
This stage establishes formal use cases and process models that define how building data will be used. It outlines information requirements and exchanges needed to support retrofit planning and ongoing commissioning.
Work Package 2: DECODER Platform development
This stage focuses on building the DECODER platform. It enables the ingestion, processing, storage, and use of building data to support both individual building and portfolio-level analysis.
Work Package 3: Building DECODER
This stage develops algorithms that assess building performance, detect and diagnose equipment faults, and optimize system controls to reduce energy use.
Work Package 4: Portfolio-level functionality
This stage enables the analysis of multiple buildings at once. It supports the identification and prioritization of retrofit strategies, and evaluates feasibility based on cost, time, and lifecycle carbon impacts.
Work Package 5: Use case implementation
This stage focuses on applying the platform in real-world settings. It includes the development of training resources and implementation across partner buildings to support adoption, refinement, and measurable impact.
DECODER brings together a multidisciplinary team of researchers and collaborators from 果酱视频 and Concordia University.
Dr. Jenn McArthur
Principal Investigator
Professor, Architectural Science, 果酱视频
Research focus: Leads DECODER Building-Level Functionality
Contact: jennifer.mcarthur@torontomu.ca
Concordia University
Research focus: DECODER Platform Development
Concordia University
Research focus: Leads the Use Case Definitions research
Concordia University
Research focus: Leads the DECODER Platform Development
Concordia University
Research focus: DECODER Platform Development
Concordia University
Research focus: Leads DECODER Portfolio-Level Functionality
Concordia University
Research focus: DECODER Platform Development
DECODER is supported through collaboration with industry, government, and institutional partners who contribute to research, implementation, and real-world validation.
Get Involved
The DECODER team is always open to expanding our impact through through collaboration with building owners, partners, researchers and decision makers.