A novel QLattice-based whitening machine learning model of landslide susceptibility mapping

Abstract

Landslide susceptibility mapping (LSM) enables the prediction of landslide occurrences, thereby offering a scientific foundation for disaster prevention and control. In recent years, numerous studies have been conducted on LSM using machine learning techniques. However, the majority of machine learning models is considered “black box” models due to their lack of transparent explanations. In contrast, the QLattice model serves as a white box model, as it can elucidate the decision-making mechanism while representing a novel approach to whitening machine learning models. QLattice possesses the capability to automatically select and scale data features. In this study, Fengjie County in China was selected as the research area, with slope units serving as evaluation units. A geospatial database was constructed using 12 conditioning factors, including elevation, slope, and annual average rainfall. LSM models were conducted using both the QLattice and random forest (RF) algorithms. The findings demonstrate that the QLattice model achieved an area under curve value of 0.868, while the RF model attained an area under curve value of 0.849 for the test datasets. These results highlight the superior predictive ability and stability of the QLattice model compared with RF. Furthermore, QLattice can explicate and clarify the change processes of conditioning factors, thereby revealing the internal decision-making mechanism and causes behind the LSM model's decisions. The innovative QLattice-based model provides new ideas and methodologies for LSM research.