Data Portal
IBDT is building a campus data portal that gives students and researchers simple, secure access to UofT building information, including:
- Structured data such as sensor data, utility data (e.g., electricity).
- Unstructured data such as building layouts, reports and other documents.
Digitization
Our goal is not to model every campus building from scratch. Instead, we focus on practical digitization: connecting existing building layouts with IoT data so teams can make faster, better decisions.
Semantic-Savvy BIM
BIM is strong for structured data, but most building knowledge lives in unstructured sources like work orders, reports, and notes. We connect both worlds so digital twins can reflect how buildings actually operate.
To do this, we use graph-based methods that link IFC/BIM concepts with semantic information from text sources. In short, we map related clusters across datasets so technical models can be enriched with operational context.
The model updates as project documents change, so links stay current over time. This creates a flexible, learning-based alternative to rigid one-time mappings.
Data Analytics for Work Orders: The What and Why
UofT processes tens of thousands of work orders every year. We analyze those records with machine learning to predict cost, duration, and repair patterns for key assets.
Beyond prediction, we focus on decision quality: what happens after specific investments, and which actions produce the strongest performance gains.
By combining structured data, work-order text, and project context, we can identify recurring issues, dependencies, and high-impact interventions.
Business Process Analysis
Operational decisions involve many priorities, constraints, and stakeholders. We use business process models to connect day-to-day workflows with the right data.
This helps teams receive timely, task-specific insights as they plan projects, evaluate options, and update operations.
Interactive Authoring Environment
We are creating an occupant-led authoring space where users can co-edit ideas, discuss options, and shape building decisions together.
Knowledge graphs help turn complex information into practical guidance, including climate risks, trade-offs, and best practices. Users can quickly explore questions such as:
- What climate: expected change in climate elements such as temperature, precipitation, storms.
- What impacts: e.g. should migration associated with climate change be considered?
- In what way: the link between hazards and performance, which has three challenges:
- Existence of relation: not every asset is sensitive to each climate hazard.
- Inter-hazard interaction: how to consider the interplay between different climate hazards.
- Relationship formula: how to quantify hazard impacts on asset performance.
- How much: delta costs associated with the positive/negative change in hazards.
Generative DT
To move beyond conventional planning, we are building a computer-assisted platform that uses generative AI to explore multiple building and operations scenarios. Our goal is to help teams discover better options, faster.
- Generate improved business process models that put occupants and sustainability at the center.
- Learn from user-generated patterns so recommendations reflect real needs and constraints.
- Use historical project and work-order outcomes to learn what works and what causes friction.
- Extract rules from real collaboration patterns instead of relying only on generic assumptions.
- Support decision-making with recommendation tools designed to improve return on investment.