An NETL study published in the Springer journal Natural Hazards highlights new capabilities for anticipating submarine landslides in the Gulf of Mexico, which can increase the safety and success of future offshore development projects.

Among hazards occurring in offshore submarine environments, landslides pose a significant risk to offshore infrastructure attached to the seafloor. Given the importance of offshore energy production, it is necessary to anticipate where future landslide events are likely to occur to support project planning and development. A recent publication by an NETL research team describes a novel technique for landslide susceptibility mapping (LSM) in the northern Gulf of Mexico.

The team integrated a data set of expert-confirmed locations of historic submarine landslides with a geographic information system database of topographical, geomorphological, geological and geochemical factors to accurately forecast potential locations of sediment instability. The results of the study indicate that areas of high and very high susceptibility were associated with steep terrain, including salt basins and escarpments, and that a robust data set is necessary to develop accurate LSM models across environmentally diverse regions.

The research paper details the use of advanced machine learning techniques in assessing submarine landslide susceptibility. This machine learning capability is part of NETL’s Ocean and Geohazard Analysis Tool, developed in support of NETL’s Environmentally Prudent Stewardship field work proposal and showcases research under NETL’s Science-based Artificial Intelligence and Machine Learning Institute. 

“This study serves as an initial assessment of the machine learning capabilities for producing accurate submarine landslide susceptibility maps given the current state of available natural hazard-related datasets,” said NETL’s MacKenzie Mark-Moser, one of the study’s co-authors. “It provides a foundation for future studies to further improve our understanding of submarine landslide dynamics, improve the accuracy of landslide susceptibility mapping in offshore regions, and provide a significant contribution to offshore hazard research.”

The full NETL study and submarine landslide data set are available for viewing. Users can also access the machine learning-informed submarine landslide susceptibility mapping tool.

NETL is a U.S. Department of Energy national laboratory that drives innovation and delivers technological solutions for an environmentally sustainable and prosperous energy future. By leveraging its world-class talent and research facilities, NETL is ensuring affordable, abundant and reliable energy that drives a robust economy and national security, while developing technologies to manage carbon across the full life cycle, enabling environmental sustainability for all Americans.