BATSCCD: a new change detection method for mapping building age in rapidly changing urban areas using Landsat time series data

Abstract

ABSTRACT The building age is an important feature in the vulnerability assessment of disasters and building energy consumption modeling. It provides indispensable information for the study of built environment. However, obtaining high-precision maps of building ages is challenging, which impedes the development of relevant research and applications. In this study, a new building age mapping method based on Landsat time series classification and change detection (BATSCCD) was proposed, which integrates Landsat time series data with random forest and LandTrendr algorithm to reflect non-building to building changes, building reconstruction, and corresponding change characteristics. The proposed method achieved overall building age mapping accuracies of 80.45% within a 2-year tolerance and 87.66% within a 3-year tolerance in Guangzhou and accuracies of 78.08% and 87.52%, respectively, in Beijing. The improvement was notable, especially compared with the continuous change detection and classification (CCDC) method, with corresponding accuracy values of 36.22% and 46.31%, respectively, in Guangzhou and 49.7% and 60.19%, respectively, in Beijing. The results suggest that the BATSCCD method can be used to accurately estimate the building age and provide reliable mapping results. Thanks to the accessibility of required data and its high accuracy of building age estimation, the proposed method exhibits great application potential.