Offshore Application of Landslide Susceptibility Mapping using Gradient Boosted Decision Trees: A Gulf of Mexico Case Study

Abstract Among natural hazards occurring offshore, submarine landslides pose a significant risk to offshore infrastructure installations attached to the seafloor. With the offshore being important for current and future energy production, there is a need to anticipate where future landslide events are likely to occur on the seafloor to support planning and development projects. Using the Gulf of Mexico (GoM) as a case study, this paper performs Landside Susceptibility Mapping (LSM) using a Gradient Boosted Decision Tree (GBDT) model to characterize the spatial patterns of submarine landslide probability over the U.S. Exclusive Economic Zone (EEZ) where water depths are greater than 120 meters. With known spatial extents of historic submarine landslides and a Geographic Information System (GIS) database of known topographical, geomorphological, geological, and geochemical factors, the resulting model was capable of accurately forecasting where the potential source location of sediment instability is more likely to occur. Results of a permutation modelling approach indicate that LSM accuracy is sensitive to training set size with accuracies becoming more stable as the number of observations increases. The influence that each input feature has on predicting landslide susceptibility was evaluated using the SHapely Additive exPlanations (SHAP) feature attribution method. Areas of high and very high susceptibility were associated with steep terrain including salt basins and escarpments. This case study serves as an initial assessment of the machine learning (ML) capabilities for producing accurate submarine landslide susceptibility maps given the current state of available natural hazard-related datasets and conveys both successes and limitations.