An AI-Based Method for Estimating the Potential Runout Distance of Post-Seismic Debris Flows

Abstract

Abstract The widely distributed sediments following an earthquake presents a continuous threat to local residential areas and infrastructure. These materials become more easily mobilized due to reduced rainfall thresholds. Before establishing an effective management plan for debris flow hazards, it is crucial to determine the potential reach of these sediments. In this study, a deep learning-based method—Dual Attention Network (DAN)—was developed to predict the runout distance of potential debris flows after the 2022 Luding Earthquake, taking into account the topography and precipitation conditions. Given that the availability of reliable precipitation data remains a challenge, attributable to the scarcity of rain gauge stations and the relatively coarse resolution of satellite-based observations, our approach involved three key steps. First, we employed the DAN model to refine the Global Precipitation Measurement (GPM) data, enhancing its spatial and temporal resolution. This refinement was achieved by leveraging the correlation between precipitation and regional environment factors (REVs) at a seasonal scale. Second, the downscaled GPM underwent calibration using observations from rain gauge stations. Third, mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were employed to evaluate the performance of both the downscaling and calibration processes. Then the calibrated precipitation, catchment area, channel length, average channel gradient, and sediment volume were selected to develop a prediction model based on debris flows following the Wenchuan Earthquake. This model was applied to estimate the runout distance of potential debris flows after the Luding Earthquake. The results show that: (1) The calibrated GPM achieves an average MAE of 1.56 mm, surpassing the MAEs of original GPM (4.25 mm) and downscaled GPM (3.83 mm); (2) The developed prediction model reduces the prediction error by 40 m in comparison to an empirical equation; (3) The potential runout distance of debris flows after the Luding Earthquake reaches 0.77 km when intraday rainfall is 100 mm, while the minimum distance value is only 0.06 km. Overall, the developed model offers a scientific support for decision makers in taking reasonable measurements for loss reduction caused by post-seismic debris flows.

Keywords

• Deep learning
• GPM downscaling
• Post-seismic debris flows
• Runout distance prediction
• 2022 Luding earthquake