Category:Decision Support and Tools

The Decision Support and Tools category provides interactive, computational, and algorithmic instruments designed to translate raw environmental data into actionable insights for building managers, researchers, and public authorities.

This section hosts the computational tools developed under EDIAQI Work Packages 4 and 6 (Task 4.4, Task 4.5, Task 6.1). It combines physics-based formulations, mass balance models, and state-of-the-art machine learning algorithms to enable proactive, data-driven indoor air quality management.

Core Instruments

• The EDIAQI Decision Tree: The structured methodological workflow guiding users from problem identification (Why?) and sensing (How?) to physical remediation (What now?).
• EDIAQI IAQ Simulation Tool: A machine learning-driven web application (developed by Know-Center using CatBoost regression and cohort data) predicting residential PM2.5 and NO2 levels based on building metadata and occupant habits.
• Hybrid Digital Twins: Integration of dense sensor networks, dynamic mass balance/decay models, and Computational Fluid Dynamics (CFD) to simulate spatial airflow fields, stagnation zones, and pollutant dispersion.
• Building Audit Frameworks: Continuous analytics tools for diagnosing HVAC inefficiencies and benchmarking indoor climate parameters.