The impact of occupancy dynamics on indoor CO2 forecasting: a cross-scenario evaluation

Indoor CO2 forecasting supports proactive ventilation control that balances air quality with energy efficiency. While Machine Learning (ML) models have shown strong performance in controlled settings such as schools, their generalization across indoor spaces with diverse occupancy dynamics remains p...

ver descrição completa

Detalhes bibliográficos
Autores: Garcia-Pinilla, Peio, Jurío Munárriz, Aránzazu, Figols, María, Paternain Dallo, Daniel
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Recursos:Universidad San Jorge (USJ)
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:dnet:academicae__::0f662a392a2ef08611d8cc4bea5342c7
Acesso em linha:https://hdl.handle.net/2454/57128
Access Level:acceso abierto
Palavra-chave:Indoor air quality
Forecasting
Machine learning
Foundation models
Indoor CO2
IoT
Descrição
Resumo:Indoor CO2 forecasting supports proactive ventilation control that balances air quality with energy efficiency. While Machine Learning (ML) models have shown strong performance in controlled settings such as schools, their generalization across indoor spaces with diverse occupancy dynamics remains poorly characterized. We present a systematic benchmark of 11 forecasting models spanning simple baselines, statistical methods, classical ML, deep learning, ensembles, and foundation models using 18 weeks of IoT sensor data spanning six real-world use cases: conference rooms, dining halls, hospitals, food markets, offices and student residences. Performance depends strongly on the prediction horizon and on the regularity of occupancy-driven CO2 patterns. Simple baselines tend to perform best at short horizons (10 min ahead), while ensembles and fine-tuned foundation models provide more robust accuracy at longer horizons (4 h ahead). Remarkably, zero-shot foundation models demonstrate the ability to outperform trained classical models in data-scarce scenarios, challenging the traditional paradigm of localized training. These findings indicate that optimal forecasting strategies are context-dependent and challenge the assumption of universal model superiority.