Underground wine cellars represent a fragile form of cultural heritage, where long-term microclimatic imbalance can lead to material degradation, structural instability, and internal collapses. High humidity, limited ventilation, and the difficulty of access complicate both diagnosis and conservation. This study presents preliminary results from a preventive monitoring strategy applied to the underground wine cellars of Baltanás (Palencia, Spain), focusing on temperature, relative humidity, wall moisture content, and ventilation as key drivers of deterioration. A wireless network of commercial temperature–humidity sensors, wall moisture probes, and airflow sensors was deployed in four sections of a representative cellar over a monitoring period exceeding two years. In addition, mobile monitoring was performed using a quadruped robot equipped with a rotating environmental sensing module, enabling measurements in confined and unstable areas. Results reveal strong thermal inertia, persistently high relative humidity frequently approaching saturation, low and intermittent natural ventilation, and sustained internal wall moisture. These conditions are consistent with observed material decay and internal landslides. The monitoring with quadruped robot proved particularly valuable for identifying localized humidity pockets and stagnant air zones beyond the reach of fixed sensors. The study demonstrates how different solutions for monitoring can support preventive conservation strategies for subterranean heritage, providing a scalable framework for early risk detection and informed management decisions.

In this paper the design, development, and validation of a set of low-power low-cost sensor systems intended for environmental monitoring and visitor tracking in cultural heritage sites are shown. These systems have been deployed in five pilot cases in four different countries in Europe inside the European ARGUS project. Two different approaches have been defined in the design: the static systems installed in fixed positions and the dynamic systems installed in a moving robot, i.e., a quadruped robot or a drone. The Baltanás pilot site has served as the primary testing platform, enabling accelerated prototyping and iterative improvement before deployment across additional pilot locations. This paper presents the design criteria, system architectures, and performance evaluation of these sensor networks, including thermal–humidity probes, volumetric water content sensors, wind measurement systems, pollution monitors, and two generations of visitor counting devices.

In this paper the design, development, and validation of a set of low power, low-cost sensor systems intended for environmental monitoring and visitor tracking in cultural heritage sites is shown. These systems have been deployed in 5 pilot cases in 4 different countries in Europe inside the European ARGUS project. Two different approaches have been defined in the design: the static systems installed in fixed positions and the dynamic systems installed in a moving robot i.e., a quadruped robot or a drone. The Baltanás pilot site has served as the primary testing platform, enabling accelerated prototyping and iterative improvement before deployment across additional pilot locations. This paper presents the design criteria, system architectures, and performance evaluation of these sensor networks, including thermal–humidity probes, volumetric water content sensors, wind measurement systems, pollution monitors, and two generations of visitor counting devices.

Radon (Rn-222) is a major indoor air pollutant with significant health risks. This work presents RadonFAN, a low-cost IoT system deployed in two galleries at the Institute of Physical and Information Technologies (ITEFI-CSIC, Madrid), integrating distributed sensors, microcontrollers, cloud analytics, and automated fan control to maintain radon concentrations below recommended limits. Initially, ventilation relied on a reactive, rule-based mechanism triggered when thresholds were exceeded. To improve preventive control, two end-to-end deep learning models based on regression-to-classification (R2C) and direct classification (DC) are developed. A quantitative analysis of predictive performance and computational efficiency is reported. While the R2C model is hindered by the inherent behavior of the time series, the DC model achieves high classification performance (recall > 0.975) with low computational cost (<4 million parameters, 7 million FLOPs). Modifications to the DC model are studied to identify potential performance bottlenecks and the most relevant components, showing that most limitations arise from feature richness and time series behavior. When evaluated against the existing rule-based ventilation system, the DC model reduces both unsafe radon exposure events and energy consumption, demonstrating its effectiveness for preventive radon mitigation.

Cultural heritage (CH) sites are continuously exposed to pressures that can lead to deterioration. Continuous monitoring and anomaly detection (AD) enable early damage detection for preventive conservation. We propose a late-fusion AD framework combining NST-Net, a nested spatiotemporal neural network, with a semantic module encoding expert conservation rules, and evaluate it on five real-world CH monitoring datasets. NST-Net outperforms six state-of-the-art baselines on most sites, achieving, on average, 42% higher Average Precision than the best baseline per site under a synthetic evaluation protocol emphasizing sharp, short-duration anomalies. Dataset length serves as an important performance factor: the combined architecture and preprocessing pipeline particularly benefit longer campaigns, whereas they add little value on shorter ones. NST-Net also requires approximately 13 times less peak memory than baseline detectors, at a higher but still millisecond-scale latency. Further analysis shows that performance depends strongly on anomaly density, type, and severity. The semantic module passes label-free sanity checks and complements NST-Net effectively (complementarity index > 0.87), identifying conservation-relevant events missed by the deep model. These findings support late-fusion statistical–semantic frameworks for AD in CH monitoring.

Unmanned aerial vehicles (UAVs) equipped with lightweight gas sensors offer a promising approach for greenhouse-gas emission monitoring. However, airflow generated by multirotor propellers can disturb the atmosphere and influence measured gas concentrations. This study investigates rotor-induced downwash effects on vehicle exhaust plume measurements using experimental and numerical approaches. Experiments were conducted with a stationary diesel vehicle at idle, while a propeller system reproduced UAV downwash at rotor-sensor separation distances of 0.5–5.5 m above a fixed CO₂ sensor. A low-cost Feather-based sensing platform was evaluated against a commercial IoTSens monitoring station. CFD simulations were performed in OpenFOAM^® using a compressible multi-species solver, Large Eddy Simulation (LES), and a Multiple Reference Frame (MRF) approach. Experiments showed CO₂ reductions of up to 52.7%, while CFD predicted reductions of 50.4–88.5%. Both approaches showed decreasing rotor-wake influence with increasing separation distance, with strongest effects below approximately 2–3 m. Experimentally, downwash effects became weak between 3.5 and 5.5 m, consistent with reduced plume–wake interaction predicted by CFD. These findings highlight the importance of accounting for rotor-induced downwash when designing UAV-based gas monitoring missions.