Fabric retrofit scenario analysis under uncertainty for an urban housing stock using machine learning
Abstract
Fabric retrofit is central to decarbonising housing, and planning it depends on expected savings and their uncertainty. This study asks which upgrade saves most per dwelling and across a housing portfolio, how uncertain the savings are, and whether upgrade order matters. We propose an uncertainty-aware framework that converts predicted changes in energy performance certificate scores after wall, roof and window upgrades into standardised energy-cost savings and emission reductions. Six machine-learning models predict the 1-100 Standard Assessment Procedure (SAP) energy-cost and environmental impact (EI) emission scores from 17 certificate descriptors. Each model's errors on similar dwellings give calibrated prediction intervals. A global-best strategy applies the most accurate model throughout; a sample-specific strategy chooses each dwelling's model using these local errors. The analysis covers 103,414 officially registered dwellings in Westminster, London. CatBoost was the global-best model, with mean absolute errors of 3.487 SAP and 4.379 EI points on held-out dwellings. Both strategies projected similar savings; under global-best, roof insulation saved most per dwelling, GBP 203 annually (uncertainty range 176-229), and wall insulation most across the portfolio, GBP 6.09 million annually (uncertainty range 5.69-6.72). For 5,382 dwellings needing all three upgrades, every order delivered the same final package, yet installing roofs, walls, then windows a year apart accumulated 54% more projected cost savings over three years than the reverse order. Emission reductions followed the same pattern. Using only certificate data, the framework helps local authorities rank measures for dwellings and portfolios and sequence upgrades to bring savings forward.
Related
- Machine learning-based thermoelectric materials screening with physical consistency and uncertainty propagation
- Does System Size Matter in Uncertainty Quantification for Machine Learning Interatomic Potentials?
- Physics-informed random neural architectures on compact boundaryless multiply connected manifolds for random-operator models in machine learning and uncertainty quantification
- Hybrid Analytical Numerical and Machine Learning Frameworks for Solving Deterministic and Stochastic Differential Equations with Stability, Convergence, and Uncertainty Quantification
- No-Disturbance-without-Uncertainty generates the Quantum set in the simplest Bell scenario
BibTeX
@misc{bai2026fabric,
title = {{Fabric retrofit scenario analysis under uncertainty for an urban housing stock using machine learning}},
author = {Yunfei Bai and Aaron Tesfa Tsion and Raúl Rosales and Barbara Shollock and Wei He},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24608},
eprint = {2610.24608},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24608},
}
RIS
TY - UNPB
TI - Fabric retrofit scenario analysis under uncertainty for an urban housing stock using machine learning
AU - Yunfei Bai
AU - Aaron Tesfa Tsion
AU - Raúl Rosales
AU - Barbara Shollock
AU - Wei He
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.24608
UR - https://arxiv.org/abs/2610.24608
AB - Fabric retrofit is central to decarbonising housing, and planning it depends on expected savings and their uncertainty. This study asks which upgrade saves most per dwelling and across a housing portfolio, how uncertain the savings are, and whether upgrade order matters. We propose an uncertainty-aware framework that converts predicted changes in energy performance certificate scores after wall, roof and window upgrades into standardised energy-cost savings and emission reductions. Six machine-learning models predict the 1-100 Standard Assessment Procedure (SAP) energy-cost and environmental impact (EI) emission scores from 17 certificate descriptors. Each model's errors on similar dwellings give calibrated prediction intervals. A global-best strategy applies the most accurate model throughout; a sample-specific strategy chooses each dwelling's model using these local errors. The analysis covers 103,414 officially registered dwellings in Westminster, London. CatBoost was the global-best model, with mean absolute errors of 3.487 SAP and 4.379 EI points on held-out dwellings. Both strategies projected similar savings; under global-best, roof insulation saved most per dwelling, GBP 203 annually (uncertainty range 176-229), and wall insulation most across the portfolio, GBP 6.09 million annually (uncertainty range 5.69-6.72). For 5,382 dwellings needing all three upgrades, every order delivered the same final package, yet installing roofs, walls, then windows a year apart accumulated 54% more projected cost savings over three years than the reverse order. Emission reductions followed the same pattern. Using only certificate data, the framework helps local authorities rank measures for dwellings and portfolios and sequence upgrades to bring savings forward.
ER -