Skip to main content
Heritage Science

Table 4 XGBoost model evaluation for Annisse Church, for prediction of episodes of indoor relative humidity outside 45–75% RH

From: Prediction of the indoor climate in cultural heritage buildings through machine learning: first results from two field tests

Prediction for next 24 h

Precision

Recall

F1-score

Humidity too high (> 75% RH)

0.74

0.83

0.78

Humidity too low

(< 45% RH)

0.96

0.29

0.45

  1. This model was based on all input parameters (temperature, relative humidity, absolute humidity, indoors and outdoors)
Back to article page