Fire risk level prediction of timber heritage buildings based on entropy and XGBoost

Abstract

The complexes of historic timber-structure buildings are extremely complicated and have various fire threats. A targeted approach to fire risk assessment of historic timber structures is conducive to focused fire plans. Due to the sparsity of the historical fire event dataset, it is quite challenging to predict the fire risk of heritage buildings based on historical fire events data. In this study, a fire risk index-driven solution is proposed based on machine learning to predict the fire risk level of timber heritage buildings. The suggested fire risk index system emphasizes the specificities of timber and historic structures, and the indicators are processed on temporal, spatial, and attribute scales. Considering the uncertainty of fire risk, this approach objectively rates the historical fire risk of heritage buildings using entropy-weighted TOPSIS. The typical machine learning model, XGBoost, is enhanced by applying the spatially unique values to predict the monthly fire risk level of a single heritage building. It solves the issue that general models only take into account the attribute characteristics of heritage buildings. Through the proposed solution, the monthly fire risk level of the heritage buildings of the Palace Museum of China in 2019 was assessed by the XGBoost model using the fire risk index data of the historical years (2016–2018). The accuracy evaluation showed that XGBoost performed better than other models (GBDT, CatBoost, Adaboost, and SVM), which is expected to provide information support for the safety inspection work of the fire department in the Palace Museum.