Our Initiatives

Practical Solutions for Real-World Problems

Data Access

A core IBDT initiative is building a data portal that makes UofT building information easier to access and use for research and operations.

Structured data such as sensor data, utility data (e.g., electricity)
Unstructured data such as building layouts, reports, and other documents

Our approach balances openness, usability, and security through three priorities:

Understanding data: define what data is shared, who needs it, why it is needed, and how quality and risk are managed.
Profiling users: understand user needs, usage patterns, and technical capabilities so access is meaningful, not just available.
Modeling usage: set clear usage modes, access duration, sharing rules, and monitoring for misuse or anomalies.

Beyond basic access, we aim to provide value-added services in three ways:

Data modeling: harmonize fragmented datasets so they can be searched, connected, and analyzed more effectively.
Data analytics: share useful insights, from simple trends to predictive models and scenario simulations.
Access policies: continuously refine governance using user feedback, usage evidence, and policy best practices.

Digitization

We are not trying to model every building from scratch. We focus on practical digitization by connecting existing layouts with IoT data, then sharing lessons that help partners adopt similar strategies.

Empowerment by Knowledge Democratization

We believe better outcomes come from shared knowledge. Our goal is to make complex building and climate information easier to understand and use.

By combining AI, knowledge graphs, and interactive tools, we help professionals and users learn together, co-create ideas, and make more informed decisions.

This approach supports stronger community participation and more resilient, sustainability-focused planning.

Linking structured and unstructured data (the graph is the new BIM)

BIM works well for structured data, but much operational knowledge is unstructured. We connect both sources so digital twins better represent real project conditions.

Using graph-based methods, we link BIM/IFC concepts with information extracted from documents and text. These links evolve as projects evolve, creating a flexible and adaptive knowledge layer.

Work Order Analytics

UofT handles a large volume of work orders every year. We analyze these records to predict cost, duration, and repair behavior.

We also study how decisions affect outcomes over time, helping teams identify high-ROI actions and improve asset management strategies.

Business Process Analysis

Operational decisions are complex and often siloed. We use business process modeling to connect tasks, data, and decision points in a practical workflow.

This helps decision-makers receive relevant insights at the right time when planning projects or updating operations.

Interactive Authoring Environment

We are creating an occupant-led authoring environment where users can co-edit ideas and discuss options using connected documents and BIM models.

Knowledge graphs will help turn diverse information into practical, searchable guidance for climate and operations planning.

Users can find answers to the following questions:

What climate: expected changes in climate elements such as temperature, precipitation, and storms.
What impacts: whether migration associated with climate change should 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.

This helps occupants and operators make informed decisions with clearer visibility into climate and performance impacts.

Generative Digital Twinning

We are building a generative digital twin approach to help teams explore more options, faster, and with stronger evidence.

Key targets include:

Generate improved business process models that place occupants and sustainability at the center.
Use patterns from user-generated solutions so recommendations reflect real needs and constraints.
Learn from project and work-order outcomes to repeat what works and avoid recurring issues.
Extract rules from real semantic and social collaboration patterns.
Support option recommendation systems that help improve decision quality and ROI.

Overall, this initiative helps teams design smarter interventions, align stakeholders, and make better evidence-based choices.