Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 11

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

AI-Driven Prediction of Building Energy Performance and Thermal Resilience During Power Outages: A BIM-Simulation Machine Learning Workflow

Mehraban, Mohammad H., Mirzabeigi, Shayan, Faraji, Setare, Soltanian-Zadeh, Sameeraa, Sepasgozar, Samad M. E.·2025·Buildings
DOI 10.3390/buildings15213950
Open this paper in CoChat — free account

Abstract

Power outages during extreme heat events threaten occupant safety by exposing buildings to rapid indoor overheating. However, current building thermal resilience assessments rely mainly on physics-based simulations or IoT sensor data, which are computationally expensive and slow to scale. This study develops an Artificial Intelligence (AI)-driven workflow that integrates Building Information Modeling (BIM)-based residential models, automated EnergyPlus simulations, and supervised Machine Learning (ML) algorithms to predict indoor thermal trajectories and calculate thermal resilience against power failure events in hot seasons. Four representative U.S. residential building typologies were simulated across fourteen ASHRAE climate zones to generate 16,856 scenarios over 45.8 h of runtime. The resulting dataset spans diverse climates and envelopes and enables systematic AI training for energy performance and resilience assessment. It included both time-series of indoor thermal conditions and static thermal resilience metrics such as Passive Survivability Index (PSI) and Weighted Unmet Thermal Performance (WUMTP). Trained on this dataset, ensemble boosting models, notably XGBoost, achieved near-perfect accuracy with an average R2 of 0.9994 and nMAE of 1.10% across time-series (indoor temperature, humidity, and cooling energy) recorded every 3 min for a 5-day simulation period with 72 h of outage. It also showed strong performance for predicting static resilience metrics, including WUMTP (R2 = 0.9521) and PSI (R2 = 0.9375), and required only 1148 s for training. Feature importance analysis revealed that windows contribute 74.3% of the envelope-related influence on passive thermal response. This study demonstrates that the novelty lies not in the algorithm itself, but in applying the model to resilience context of power outages, to reduce computations from days to seconds. The proposed workflow serves as a scalable and accurate tool not only to support resilience planning, but also to guide retrofit prioritization and inform building codes.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/buildings15213950

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 62

  1. Schulz, 2010, Lessons from the London Climate Change Strategy: Focusing on Combined Heat and Power and Distributed Generation, J. Urban Technol., 17, 3, 10.1080/10630732.2010.553038 · DOI
  2. Keirstead, 2012, A review of urban energy system models: Approaches, challenges and opportunities, Renew. Sustain. Energy Rev., 16, 3847, 10.1016/j.rser.2012.02.047 · DOI · Paper page
  3. Rehman, H.u., Nik, V.M., Ramesh, R., and Ala-Juusela, M. (2024). Quantifying and Rating the Energy Resilience Performance of Buildings Integrated with Renewables in the Nordics under Typical and Extreme Climatic Conditions. Buildings, 14. · DOI
  4. Chen, 2018, Recent Progress and Emerging Topics on Weather and Climate Extremes Since the Fifth Assessment Report of the Intergovernmental Panel on Climate Change, Annu. Rev. Environ. Resour., 43, 35, 10.1146/annurev-environ-102017-030052 · DOI
  5. Steinhaeuser, 2012, Multivariate and multiscale dependence in the global climate system revealed through complex networks, Clim. Dyn., 39, 889, 10.1007/s00382-011-1135-9 · DOI
  6. Auffhammer, 2014, Measuring climatic impacts on energy consumption: A review of the empirical literature, Energy Econ., 46, 522, 10.1016/j.eneco.2014.04.017 · DOI
  7. Belusko, 2016, Heat stress risk and resilience in the urban environment, Sustain. Cities Soc., 26, 278, 10.1016/j.scs.2016.06.019 · DOI
  8. Belusko, 2016, Drivers and barriers to heat stress resilience, Sci. Total Environ., 571, 603, 10.1016/j.scitotenv.2016.07.028 · DOI
  9. Keramitsoglou, 2017, Urban thermal risk reduction: Developing and implementing spatially explicit services for resilient cities, Sustain. Cities Soc., 34, 56, 10.1016/j.scs.2017.06.006 · DOI
  10. Rafael, 2016, Influence of urban resilience measures in the magnitude and behaviour of energy fluxes in the city of Porto (Portugal) under a climate change scenario, Sci. Total Environ., 566–567, 1500, 10.1016/j.scitotenv.2016.06.037 · DOI
  11. Mola, 2018, Energy resilience: Research trends at urban, municipal and country levels, Energy Procedia, 147, 104, 10.1016/j.egypro.2018.07.039 · DOI
  12. Sun, 2021, Passive cooling designs to improve heat resilience of homes in underserved and vulnerable communities, Energy Build., 252, 111383, 10.1016/j.enbuild.2021.111383 · DOI · Paper page
  13. Hong, 2023, Ten questions concerning thermal resilience of buildings and occupants for climate adaptation, Build. Environ., 244, 110806, 10.1016/j.buildenv.2023.110806 · DOI · Paper page
  14. Ozarisoy, 2022, Energy effectiveness of passive cooling design strategies to reduce the impact of long-term heatwaves on occupants’ thermal comfort in Europe: Climate change and mitigation, J. Clean. Prod., 330, 129675, 10.1016/j.jclepro.2021.129675 · DOI
  15. Attia, 2021, Resilient cooling of buildings to protect against heat waves and power outages: Key concepts and definition, Energy Build., 239, 110869, 10.1016/j.enbuild.2021.110869 · DOI · Paper page
  16. Sailor, 2019, The growing threat of heat disasters, Environ. Res. Lett., 14, 054006, 10.1088/1748-9326/ab0bb9 · DOI
  17. Rahmani, 2022, Exploring the thermal behaviour of building materials: Terracotta, concrete hollow block and hollow brick, under the arid climate, case study of Biskra-Algeria, Mater. Today Proc., 58, 1380, 10.1016/j.matpr.2022.02.237 · DOI
  18. Mirzabeigi, S., and Razkenari, M. (2022, January 11–12). Multiple benefits through residential building energy retrofit and thermal resilient design. Proceedings of the 6th Residential Building Design & Construction Conference, University Park, PA, USA.
  19. Sepasgozar, S., Karimi, R., Farahzadi, L., Moezzi, F., Shirowzhan, S.M., Ebrahimzadeh, S., Hui, F., and Aye, L. (2020). A Systematic Content Review of Artificial Intelligence and the Internet of Things Applications in Smart Home. Appl. Sci., 10. · DOI
  20. Saleem, 2022, Explaining deep neural networks: A survey on the global interpretation methods, Neurocomputing, 513, 165, 10.1016/j.neucom.2022.09.129 · DOI
  21. Kondath, N., Myat, A., Soh, Y.L., Tung, W.L., Eugene, K.A.M., and An, H. (2024). Enhancing Day-Ahead Cooling Load Prediction in Tropical Commercial Buildings Using Advanced Deep Learning Models: A Case Study in Singapore. Buildings, 14. · DOI
  22. Abdel-Jaber, F., and Dirks, K.N. (2024). A Review of Cooling and Heating Loads Predictions of Residential Buildings Using Data-Driven Techniques. Buildings, 14. · DOI
  23. Gong, Y., Zoltán, E.S., and Gyergyák, J. (2023). A Neural Network Trained by Multi-Tracker Optimization Algorithm Applied to Energy Performance Estimation of Residential Buildings. Buildings, 13. · DOI
  24. Mehraban, M.H., Alnaser, A.A., and Sepasgozar, S.M.E. (2024). Building Information Modeling and AI Algorithms for Optimizing Energy Performance in Hot Climates: A Comparative Study of Riyadh and Dubai. Buildings, 14. · DOI
  25. Muslimsyah, M., Safwan, S., and Novandri, A. (2025). Comprehensive Assessment of Indoor Thermal in Vernacular Building Using Machine Learning Model with GAN-Based Data Imputation: A Case of Aceh Region, Indonesia. Buildings, 15. · DOI
  26. Tahmasebinia, F., Jiang, R., Sepasgozar, S., Wei, J., Ding, Y., and Ma, H. (2022). Implementation of BIM Energy Analysis and Monte Carlo Simulation for Estimating Building Energy Performance Based on Regression Approach: A Case Study. Buildings, 12. · DOI
  27. Qin, H., Yu, Z., Li, Z., Li, H., and Zhang, Y. (2024). Nearly Zero-Energy Building Load Forecasts through the Competition of Four Machine Learning Techniques. Buildings, 14. · DOI
  28. Abdel-Jaber, F., and Dirks, K.N. (2024). Thermal Load Prediction in Residential Buildings Using Interpretable Classification. Buildings, 14. · DOI
  29. Aparicio-Ruiz, P., Barbadilla-Martín, E., Guadix, J., and Nevado, J. (2023). Analysis of Variables Affecting Indoor Thermal Comfort in Mediterranean Climates Using Machine Learning. Buildings, 13. · DOI
  30. Liu, H., and Ma, E. (2023). An Explainable Evaluation Model for Building Thermal Comfort in China. Buildings, 13. · DOI
  31. Mehraban, 2025, AI-enhanced automation of building energy optimization using a hybrid stacked model and genetic algorithms: Experiments with seven machine learning techniques and a deep neural network, Results Eng., 26, 104994, 10.1016/j.rineng.2025.104994 · DOI
  32. Norouzi, P., Maalej, S., and Mora, R. (2023). Applicability of Deep Learning Algorithms for Predicting Indoor Temperatures: Towards the Development of Digital Twin HVAC Systems. Buildings, 13. · DOI
  33. Iqbal, F., and Mirzabeigi, S. (2025). Digital Twin-Enabled Building Information Modeling–Internet of Things (BIM-IoT) Framework for Optimizing Indoor Thermal Comfort Using Machine Learning. Buildings, 15. · DOI
  34. Akander, J., Bakhtiari, H., Ghadirzadeh, A., Mattsson, M., and Hayati, A. (2024). Development of an AI Model Utilizing Buildings’ Thermal Mass to Optimize Heating Energy and Indoor Temperature in a Historical Building Located in a Cold Climate. Buildings, 14. · DOI
  35. Telicko, J., Krumins, A., and Nikitenko, A. (2025). Development and Evaluation of Neural Network Architectures for Model Predictive Control of Building Thermal Systems. Buildings, 15. · DOI
  36. Krelling, 2023, A simulation framework for assessing thermally resilient buildings and communities, Build. Environ., 245, 110887, 10.1016/j.buildenv.2023.110887 · DOI
  37. Wang, 2024, Digital twin approach for enhancing urban resilience: A cycle between virtual space and the real world, Resilient Cities Struct., 3, 34, 10.1016/j.rcns.2024.06.002 · DOI
  38. Zhang, 2021, A review of machine learning in building load prediction, Appl. Energy, 285, 116452, 10.1016/j.apenergy.2021.116452 · DOI
  39. Li, 2025, A digital twin platform for building performance monitoring and optimization: Performance simulation and case studies, Build. Simul., 18, 1561, 10.1007/s12273-025-1290-2 · DOI
  40. Tao, 2025, Assessment of thermal comfort and thermal resilience in dwellings during heat waves: A case study of a near-zero energy house, J. Build. Eng., 109, 113052, 10.1016/j.jobe.2025.113052 · DOI
  41. Ismail, 2023, Quantifying thermal resilience of office buildings during power outages: Development of a simplified model metric and validation through experimentation, J. Build. Eng., 72, 106564, 10.1016/j.jobe.2023.106564 · DOI
  42. Sheng, 2023, Assessing thermal resilience of an assisted living facility during heat waves and cold snaps with power outages, Build. Environ., 230, 110001, 10.1016/j.buildenv.2023.110001 · DOI · Paper page
  43. Homaei, 2021, Thermal resilient buildings: How to be quantified? A novel benchmarking framework and labelling metric, Build. Environ., 201, 108022, 10.1016/j.buildenv.2021.108022 · DOI
  44. Mirzabeigi, S., Homaei, S., Razkenari, M., and Hamdy, M. (2023). The Impact of Building Retrofitting on Thermal Resilience Against Power Failure: A Case of Air-Conditioned House. Proceedings of the 5th International Conference on Building Energy and Environment, Springer. · DOI
  45. Izenman, A.J. (2008). Modern Multivariate Statistical Techniques, Springer. Available online: https://link.springer.com/book/10.1007/978-0-387-78189-1. · DOI
  46. Pedregosa, 2011, Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12, 2825
  47. Kohavi, R. (1995, January 20–25). A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.
  48. Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press Cambridge.
  49. Shavitt, I., and Segal, E. (2018). Regularization learning networks: Deep learning for tabular datasets. Adv. Neural Inf. Process. Syst., 31, Available online: https://proceedings.neurips.cc/paper_files/paper/2018/hash/500e75a036dc2d7d2fec5da1b71d36cc-Abstract.html.
  50. Xu, L., Skoularidou, M., Cuesta-Infante, A., and Veeramachaneni, K. (2019). Modeling tabular data using conditional gan. Adv. Neural Inf. Process. Syst., 32.
  51. Lundberg, S.M., Erion, G.G., and Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv.
  52. Arik, 2021, TabNet: Attentive Interpretable Tabular Learning, Proc. AAAI Conf. Artif. Intell., 35, 6679
  53. Breiman, L., Friedman, J., Olshen, R.A., and Stone, C.J. (2017). Classification and Regression Trees, Chapman and Hall/CRC. · DOI · Paper page
  54. Breiman, 2001, Random forests, Mach. Learn., 45, 5, 10.1023/A:1010933404324 · DOI · Paper page
  55. Friedman, 2001, Greedy function approximation: A gradient boosting machine, Ann. Stat., 29, 1189, 10.1214/aos/1013203451 · DOI · Paper page
  56. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Adv. Neural Inf. Process. Syst., 31.
  57. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst., 30.
  58. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA. · DOI · Paper page
  59. Bischl, 2023, Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges, Wiley Interdiscip. Rev. Data Min. Knowl. Discov., 13, e1484, 10.1002/widm.1484 · DOI
  60. Snoek, J., Larochelle, H., and Adams, R.P. (2012). Practical bayesian optimization of machine learning algorithms. Adv. Neural Inf. Process. Syst., 25.
  61. Figueiredo Filho, D.B., Júnior, J.A.S., and Rocha, E.C. (2011). What is R2 all about?. Leviathan, 60–68. · DOI
  62. Roider, 2024, Assessing the Performance of Remaining Time Prediction Methods for Business Processes, IEEE Access, 12, 130583, 10.1109/ACCESS.2024.3459648 · DOI

Metadata

Authors
Mehraban, M. H., Mirzabeigi, S., Faraji, S., Soltanian-Zadeh, S., & Sepasgozar, S. M. E.
Venue
Buildings
Publisher
MDPI AG
Published
2025-11-02
Volume
15
Issue
21
Pages
3950
ISSN
2075-5309
DOI
10.3390/buildings15213950
Cited by
11
References
3
Language
en
Licence
creativecommons.org/licenses/by/4.0/ (vor)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.