FORGE
Research organized around papers, projects, and standards work.
FORGE currently concentrates on four connected lines of work: human heat and
thermal comfort, climate forcing and future weather, control and co-simulation,
and ventilation or design-facing systems. The themes below are pulled directly
from recent papers, grants, and ongoing student projects rather than generic
academic categories.
Current track 01
Human heat, comfort, and standards
Research here spans demographic metabolic rates, MRT-aware comfort analysis, ordinal prediction, and physiology-constrained models. The through-line is to replace abstract default occupants with measurable human heat and comfort response.
Current track 02
Climate futures and stochastic weather
FORGE studies how future weather assumptions alter building performance using climate forcing, ERA5 or CMIP chains, stochastic generation, and uncertainty propagation. The goal is not just future files, but defensible stress-tests for design and operation.
Current track 03
Operation, ventilation, and design-facing systems
Work extends from EnergyPlus co-simulation and risk-aware control to wet-market ventilation retrofits and AI-supported pedagogy platforms. The point is to turn models into operational, institutional, and design tools rather than leaving them as standalone predictions.
- Ordinal and probabilistic thermal comfort prediction from seven-point sensation votes
- Physics-informed neural networks with physiological constraints
- Mean radiant temperature sensitivity analysis for HVAC control
- Demographic-aware metabolic-rate modeling and ASHRAE standards revision
- Fan-assisted cooling, gender differences, and cross-cultural comfort evidence
- Climate-adapted weather file evaluation using causal decomposition of degree-day errors
- Scenario-conditioned and stochastic weather generation from long observational records
- ERA5 / CMIP6 forcing chains for climate stress-testing
- Monte Carlo propagation and uncertainty benchmarking across future scenarios
- Building performance evaluation under climate-stressed futures through 2100
- EnergyPlus-based co-simulation for occupant-aware building control
- Risk-aware control framing from probabilistic comfort outputs
- Interpretable ML, feature attribution, and sensitivity tracing
- Indoor temperature forecasting and competition-tested predictive workflows
- Digital twins that connect learned models to operational testing
- Wet-market ventilation retrofits and IEQ-energy trade-off analysis
- Field measurement in mixed-mode and public-building contexts
- Design pedagogy systems such as Socratic Oracle and AI Design Coach
- Evidence-based generative design workflows for architecture education
- Research legible to design studios, standards work, and public-sector collaboration
- Kanxuan He, PhD (HKU, 2025-): probabilistic control; first place at the ICML 2025 CO-BUILD Smart Building Competition.
- Yu Chang, PhD (HKU, 2024-): cross-cultural thermal comfort; first-author review in Renewable and Sustainable Energy Reviews (2025).
- Multi-agentic, physics-informed occupant modeling for environmental evaluation in architectural design.
- Neuroarchitecture thesis using EEG to study occupant responses to spatial design conditions.
- ASHRAE Research Project 1959-TRP, PI, awarded February 2026 and commencing April 2026.
- Teaching Development and Language Enhancement Grant, HKU, PI, Socratic Oracle (2025-2028).
- Teaching Development Grant, HKU, PI, AI Design Coach (2026-2028).
- ICML 2025 CO-BUILD Smart Building Competition, first place as faculty mentor and author.
- NeurIPS 2025 Urban AI Workshop Buildings Challenge, third place as faculty mentor.
- Gartner Eye on Innovation Award, BNY Mellon, 2021.
- Lowry Methodology Award, International Conference of Urban Climate, 2018.
FORGE sits between standards work, building simulation, comfort science, and
design pedagogy. The aim is to build methods rigorous enough for climate-risk
analysis, validation, and technical decision-making, but clear enough to inform
architectural judgment, studio teaching, and public-sector collaboration.