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 2 resolution between 2005 and 2017 over a~100 km 2 area. Models trained on~1% of full-coverage depth change data produce comparable and relatively low average predicted depth change errors (1-2 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.Plain Language Summary Many river deltas worldwide have unstable seabeds that move vertically and laterally on yearly intervals, threatening seafloor infrastructure such as communication cables and pipelines. A common method to measure seabed movement is with repeat bathymetric surveys, which are expensive and require considerable expertise. Here we introduce a new method that greatly reduces the resurvey data required to assess seabed instability: using geospatial models to estimate depth change where it is not measured. We test three different models trained on a small amount (1% of complete resurvey coverage) of Mississippi River Delta Front (MRDF) depth change data and find the predicted depth change is comparably accurate (1-2 cm error) for all methods. We recommend the K-nearest neighbors machine learning method of the three, as it produces the most geologically realistic estimates and can predict depth change from multiple types of resurvey data. This method is applicable to MRDF-like deltas and can be modified to predict depth change in different geologic environments as well.

Global Nitrogen Mass Flux From the Active Freshwater Aquifer Element Pool

“…For this study, we substituted terrestrial environmental parameters and predicted continental nitrogen concentrations. The GML we are using has been described in more detail and demonstrated on a variety of geologic parameters and recently published in the marine geology and geophysics literature (e.g., Eymold et al., 2021; Graw et al., 2020; Lee et al., 2020; Lee et al., 2020; Martin et al., 2015; Obelcz et al., 2020; Phrampus et al., 2020; Restrepo et al., 2020, 2021).…”

Seismic and Acoustic Monitoring of Submarine Landslides: Ongoing Challenges, Recent Successes and Future Opportunities

“…There is a wealth of existing onshore (and to a limited extent offshore) broadband seismic datasets in several regions where the same approach could be taken, to investigate whether similar landslide-like signals exist, if they can be located spatially, and if they correspond to any of the recent direct measurements of slope instability and their run-out, or existing maps of landslide vulnerability (e.g. Paul et al, 2018;Urlaub et al, 2018;Obelcz et al, 2020;Gamboa et al, 2021). We suggest that detailed bathymetric surveys should be performed in areas where seismic signals attributed to submarine landslides have been located to determine which types of landslide are recorded, as well as to the test the efficacy of landslide detection.…”

“…Le Friant et al, 2010;Caplan-Auerbach et al, 2014;Hunt et al, 2021), offshore river deltas (e.g. Lintern et al, 2016;Obelcz et al, 2017), including across the Mississippi submarine delta where seafloor infrastructure is threatened by submarine slope failures (Chaytor et al, 2020;Obelcz et al, 2020). The footprint of these surveys tends to be quite limited; hence, it will most likely be necessary to target specific areas, focusing on acquiring high-resolution bathymetric data that enables identification of landslide scars and/or deposits.…”

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

“…While most of the LSM studies have been conducted on terrestrial systems, little is known about the capability of LSM in regards to submarine landslides (Reichenbach et al 2018) as these methods have seldomly been applied to submarine environments (Shan et al 2021). Similar submarine slope instability assessments have been completed (i.e., Hitchcock et al 2010;Collico et al 2020;Obelcz et al 2020), however, there is a need to further understand the submarine application of LSM at larger scales. This paper presents the application of LSM to an offshore region, using the northern GoM as a case study.…”