María Figols

Mrs. María Figols


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 March 2026 in Forecasting
Verified
Journal Article
Open access
PDF file
PGPeio Garcia-Pinilla
Peio Garcia-Pinilla
AMAranzazu Jurio Munarriz
Aranzazu Jurio Munarriz
MFMaría Figols
María Figols
Daniel PaternainDaniel Paternain
Daniel Paternain
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.
1

14 September 2026 in Atmosphere
Verified
Journal Article
Open access
PDF file
JFJose Fermoso
Jose Fermoso
SRSandra Rodríguez
Sandra Rodríguez
ARAlberto Rodríguez
Alberto Rodríguez
Silvia SuárezSilvia Suárez
Silvia Suárez
JUJavier Dieguez Uribeondo
Javier Dieguez Uribeondo
RGRubèn González-Colom
Rubèn González-Colom
Indoor air quality (IAQ) in healthcare environments is affected by dynamic interactions between occupancy, ventilation, operational activities, and indoor emission sources, which are not always captured through conventional punctual assessments. This study evaluated long-term IAQ dynamics in different hospital microenvironments using continuous low-cost sensor monitoring combined with targeted chemical characterization of volatile organic compounds (VOCs) and specific aldehydes. Continuous monitoring was conducted from June 2023 to December 2025, measuring CO2, PM2.5, PM10, formaldehyde (CH2O), temperature, relative humidity, and total VOCs (TVOC). A total of 1.79 million raw records were processed, generating 1.42 million indoor measurements and 264,311 hourly aggregated observations. Complementary VOC and aldehyde sampling campaigns supported the interpretation of pollutant specific temporal patterns. Results revealed differentiated and recurrent IAQ signatures across hospital areas. CO2 dynamics were mainly associated with occupancy and ventilation demand, whereas formaldehyde showed more persistent and seasonally dependent sensor patterns, compatible with the influence of indoor emission sources and ventilation heterogeneity. Targeted chemical characterization further identified area specific pollutant profiles associated with cleaning activities, laboratory processes, materials, and operational conditions. Importantly, recurrent periods were identified in which acceptable occupancy related CO2 conditions coincided with elevated chemical pollutant levels. These findings show how long-term multi-parameter monitoring can distinguish function and pollutant specific IAQ signatures that would remain obscured by aggregated or single parameter assessments, providing an evidence base for area specific monitoring strategies and future adaptive hospital IAQ management.