Global landslide susceptibility prediction based on the automated machine learning (AutoML) framework

Landslide susceptibility prediction (LSP) is an important step for landslide hazard and risk assessment. Automated machine learning (AutoML) has the advantages of automatically features, models, and parameters selection. In this study, we proposed an AutoML-based global LSP framework at two spatial resolutions of 90 m and 1000 m, and achieved an area under the receiver operating characteristic above 0.96. The global prediction results were then validated using additional regional landslide inventories, including three countries, three provinces, and two prefecture-level datasets. Moreover, the global prediction results of 90 m are used to improve the performance of regional LSP. Specifically, the low-and very low-prone areas in the global prediction results were used as non-landslide samples for susceptibility modeling. Results demonstrated that the model achieved a better performance than original global prediction results. We believe that this study will be able to reliably promote the application of intelligent learning methods in global LSP.

Automated summary

In this study, an AutoML-based global landslide susceptibility prediction framework was proposed and achieved good performance. The framework made predictions at two spatial resolutions and used the global prediction results at 90 m to improve regional predictions. The results showed that the model outperformed the original global predictions and can reliably promote the use of intelligent learning methods in global landslide susceptibility prediction.