9 Advances in Geologic Mapping, Databases, and Dissemination: Student Posters
This session will showcase student projects associated with new geologic maps, mapping techniques, and advances in data management, web accessibility, and applications. We welcome submissions with relevance to hazards, natural resource evaluations, and water-land management.
Monday, 9 March 2026
9:00 AM - 5:00 PM
RCC, Lower Level Hall
Assessing the Relationship Between Subsurface Geology and Surficial Geomorphology: Remotely Predicting Geologic Features and Geohazards Using an Elevation-Trained Machine Learning Algorithm in the Northern Gulf of Mexico
Paper number: 9-0
Program: Technical Sessions
Time: 9:00 AM – 9:00 AM
Authors
Abstract
The growing availability of remotely derived elevation datasets for largely inaccessible regions like planetary bodies and the deep seafloor has created new opportunities to analyze terrain morphology, yet coincident subsurface geologic information remains limited in these areas due to survey cost and logistical constraints. This research evaluates the extent to which geomorphological characteristics derived from seafloor elevation data can be used to predict subsurface geological features in the Northern Gulf of Mexico. Specifically, Maximum Entropy Presence-Only (MaxEnt) spatial distribution modeling was used to predict the presence of seafloor geological features (e.g. faults, liquid and gaseous seeps, pockmarks and mud volcanoes, etc.) from integrated quantitative geomorphological data derived from seafloor bathymetry (e.g. geomorphons, BPI, slope, rugosity, curvature, aspect).The predictive skill of the resulting models was quantitatively evaluated using k-fold cross validation.
In addition to geologic feature prediction, the capacity of this modeling approach to predict landslide susceptibility was also evaluated. Specifically, this approach quantified the morphology of intact slopes adjacent to documented slope failures rather than that of the centroids of post-landslide areas. This method was designed to more accurately capture the pre-failure surface conditions that contribute to slope instability in regions influenced by salt tectonics, rapid sedimentation, and fluid overpressure.
The presented probabilistic modeling approach is intended to evaluate the extent to which elevation-derived variables and morphology can predict locations with high likelihoods of faults, fluid-migration pathways, or landslide potential. To assess the applicability of this remote prediction on a planetary body, the modeling approach was applied to a Mars analog using orbital elevation data with the overall goal of establishing a transferable model for inferring faulting and geohazard potential from surface elevation data.
Geological Society of America Abstracts with Programs. Vol. 58, No. 1
doi: 10.1130/abs/2026SE-411516
© Copyright 2026 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.