Machine Learning Augmented Time-Lapse Bathymetric Surveys: A Case Study From the Mississippi River Delta Front

Abstract

The subaqueous Mississippi River Delta Front is prone to seabed instabilities >1 m of vertical bathymetric change per year, but the ability to predict the location and magnitude of instability-driven depth change is limited. Here we demonstrate that data-driven geospatial models can predict MRDF depth change from a small amount (1% of full coverage) of training data. We predict depth change at 100 m resolution between 2005 and 2017 over a ~100 km^2 area. Models trained on ~1% of fullcoverage depth change data produce comparable and relatively low average predicted depth change errors (12 cm). K nearest neighbors best reproduce the spatial variability of depth change and can interpolate and extrapolate from training data. This approach has immediate applications for geohazard monitoring on the MRDF and other geologically similar settings and can be applied in other settings if the drivers of depth change variance are well known.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 08, 2021
Accession Number
AD1156846

Entities

People

  • Jeffrey Obelcz

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Space

DTIC Thesaurus Topics

  • Case Studies
  • Data Sets
  • Dimensionality Reduction
  • Geology
  • Information Science
  • Machine Learning
  • Marine Geology
  • Measurement
  • Mississippi
  • Mississippi River
  • Planetary Sciences
  • Pressure Measurement
  • Probability Distributions
  • Statistics
  • Supervised Machine Learning
  • Surveys
  • Turbidity Currents

Fields of Study

  • Environmental science

Readers

  • Coastal Oceanography
  • Computational Modeling and Simulation
  • Riverine Ecology

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference