TY - JOUR
T1 - Prediction of the indoor climate in cultural heritage buildings through machine learning: first results from two field tests
AU - Boesgaard, Christian
AU - Vinther Hansen, Birgit
AU - Bøgvad Kejser, Ulla
AU - Mollerup, Søren
AU - Ryhl-Svendsen, Morten
AU - Torp-Smith, Noah
PY - 2022
Y1 - 2022
N2 - Control of temperature and relative humidity in storage areas and exhibitions is crucial for long-term preservation of cultural heritage objects. This paper explores the possibilities for developing a proactive system, based on a machine-learning model (XGBoost), for predicting the occurrence of unwanted indoor environmental conditions: either a too high or a too low relative humidity, within the forthcoming 24 h. The features used in the model were hourly indoor and outdoor climate recordings, and it was applied to two indoor heritage environments; a storage facility and a church building. The test accuracy (f1-score) of the model was good (0.93 for high RH; 0.93 for low RH) when applied to the storage building, but only 0.78; 0.62 (high RH; low RH) for the church building test. Challenges encountered include difficulties in obtaining good historical climate data sets for training and testing the model, and the dependency of external IT systems, which, if they fail, inactivates the model without a warning. Several issues call for more research: A desirable improvement of the model would be predictions for periods longer than 24 h ahead, still maintaining a high test accuracy. Further perspectives of using machine learning for indoor environmental forecasting could be for indoor air pollution, or energy consumption due to climate control.
AB - Control of temperature and relative humidity in storage areas and exhibitions is crucial for long-term preservation of cultural heritage objects. This paper explores the possibilities for developing a proactive system, based on a machine-learning model (XGBoost), for predicting the occurrence of unwanted indoor environmental conditions: either a too high or a too low relative humidity, within the forthcoming 24 h. The features used in the model were hourly indoor and outdoor climate recordings, and it was applied to two indoor heritage environments; a storage facility and a church building. The test accuracy (f1-score) of the model was good (0.93 for high RH; 0.93 for low RH) when applied to the storage building, but only 0.78; 0.62 (high RH; low RH) for the church building test. Challenges encountered include difficulties in obtaining good historical climate data sets for training and testing the model, and the dependency of external IT systems, which, if they fail, inactivates the model without a warning. Several issues call for more research: A desirable improvement of the model would be predictions for periods longer than 24 h ahead, still maintaining a high test accuracy. Further perspectives of using machine learning for indoor environmental forecasting could be for indoor air pollution, or energy consumption due to climate control.
KW - Relative humidity
KW - Indoor environment
KW - Prediction
KW - Climate forecast
KW - Environmental control
KW - Storage
KW - Church building
KW - Time-series analysis
UR - https://doi.org/10.5281/zenodo.6589119
U2 - https://doi.org/10.1186/s40494-022-00805-3
DO - https://doi.org/10.1186/s40494-022-00805-3
M3 - Journal article
SN - 2050-7445
VL - 10
JO - Heritage Science
JF - Heritage Science
M1 - 176
ER -