Machine learning and engineering feature approaches to detect events perturbing the indoor microclimate in Ringebu and Heddal stave churches (Norway)

Abstract

PurposeClimate-induced damage is a pressing problem for the preservation of cultural properties. Their physical deterioration is often the cumulative effect of different environmental hazards of variable intensity. Among these, fluctuations of temperature and relative humidity may cause nonrecoverable physical changes in building envelopes and artifacts made of hygroscopic materials, such as wood. Microclimatic fluctuations may be caused by several factors, including the presence of many visitors within the historical building. Within this framework, the current work is focused on detecting events taking place in two Norwegian stave churches, by identifying the fluctuations in temperature and relative humidity caused by the presence of people attending the public events.Design/methodology/approachThe identification of such fluctuations and, so, of the presence of people within the churches has been carried out through three different methods. The first is an unsupervised clustering algorithm here termed “density peak,” the second is a supervised deep learning model based on a standard convolutional neural network (CNN) and the third is a novel ad hoc engineering feature approach “unexpected mixing ratio (UMR) peak.”FindingsWhile the first two methods may have some instabilities (in terms of precision, recall and normal mutual information [NMI]), the last one shows a promising performance in the detection of microclimatic fluctuations induced by the presence of visitors.Originality/valueThe novelty of this work stands in using both well-established and in-house ad hoc machine learning algorithms in the field of heritage science, proving that these smart approaches could be of extreme usefulness and could lead to quick data analyses, if used properly.

Sustainable management of heritage buildings in long-term perspective (SyMBoL): current knowledge and further research needs

“…This SI presents several contributions related to the development of robust methods based on ML algorithms for studying and predicting the indoor microclimate into HHBs. Both the two contributions by Manara et al (2022) and Miglioranza et al (2022) focus on microclimate of the SyMBoL case studies in Ringebu and Heddal (Norway). Currently, microclimate monitoring in HHBs is often carried out for very limited periods of time-especially when no dedicated budgets are allocated-or for longer periods of time but with sensors that are not calibrated over the years or that do not receive the needed maintenance.…”

“…As a matter of fact, this would lead towards smarter choices for the management of the indoor microclimate for preventive conservation by limiting time and money in consuming on-the-field monitoring campaigns. The second contribution by Miglioranza et al (2022) focuses on the study of microclimatic fluctuations caused by the presence of many visitors within the historic building. The work proposes a new algorithm for detecting events taking place in Ringebu and Heddal stave churches, by identifying the fluctuations in T and RH caused by the presence of people.…”

“…Both the two contributions by Manara et al. (2022) and Miglioranza et al. (2022) focus on microclimate of the SyMBoL case studies in Ringebu and Heddal (Norway).…”