A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory
Seafloor properties, including total organic carbon (TOC) and the vertical thickness (isochores) of geological units, are sparsely measured on a global scale and spatial interpolation (prediction) techniques are often used as a proxy for observations. Previous geospatial interpolations of seafloor T...
Main Author: | |
---|---|
Format: | Text |
Language: | unknown |
Published: |
Scholars Junction
2021
|
Subjects: | |
Online Access: | https://scholarsjunction.msstate.edu/td/5280 https://scholarsjunction.msstate.edu/context/td/article/6280/viewcontent/taylor_lee_dissertation.pdf |
id |
ftmississippistu:oai:scholarsjunction.msstate.edu:td-6280 |
---|---|
record_format |
openpolar |
spelling |
ftmississippistu:oai:scholarsjunction.msstate.edu:td-6280 2024-09-15T18:18:42+00:00 A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory Lee, Taylor Runyan 2021-08-06T07:00:00Z application/pdf https://scholarsjunction.msstate.edu/td/5280 https://scholarsjunction.msstate.edu/context/td/article/6280/viewcontent/taylor_lee_dissertation.pdf unknown Scholars Junction https://scholarsjunction.msstate.edu/td/5280 https://scholarsjunction.msstate.edu/context/td/article/6280/viewcontent/taylor_lee_dissertation.pdf Theses and Dissertations Earth science geology marine geology machine learning geospatial geophysics text 2021 ftmississippistu 2024-07-19T04:42:46Z Seafloor properties, including total organic carbon (TOC) and the vertical thickness (isochores) of geological units, are sparsely measured on a global scale and spatial interpolation (prediction) techniques are often used as a proxy for observations. Previous geospatial interpolations of seafloor TOC exhibit gaps where little to no observed data exists. Recent machine learning techniques, based upon a suite of geophysical and geochemical properties (e.g., seafloor biomass, porosity, distance from coast) show promise in making globally complete, comprehensive, and statistically robust geospatial seafloor predictions. Here I apply a non-parametric (i.e., data-driven) machine learning (ML) algorithm, specifically k-nearest neighbors (kNN), to estimate the global distribution of seafloor TOC and marine isochores. This machine learning approach shows major advantages relative to geospatial interpolation, including results that are quantitative, easily updatable, accompanied with uncertainty estimation, and agnostic to spatial gaps in observations. Additionally. analysis of parameter space sample density provides a guide for future sampling. Resulting predictions of the global distribution of seafloor TOC and marine isochore thicknesses were used with ML workflow to predict other seafloor parameters (e.g., heat flow, temperature, salinity) in order to constrain the global distribution of the base of hydrate stability zone and methane generation for all sub-seafloor sediments. Estimating global carbon budgets is first-order dependent on accurate model input, therefore our estimate of the base of hydrate stability zone, and subsequent carbon and methane accumulation in the subseafloor yields improvement over the standard interpolation techniques used in previous global modeling analyses. By using these globally updateable machine learning parameters as the input to predictions, results provide easily updated global budgets of total carbon and methane generated. This dissertation presents valuable new global ... Text Methane hydrate Scholars Junction - Mississippi State University Institutional Repository |
institution |
Open Polar |
collection |
Scholars Junction - Mississippi State University Institutional Repository |
op_collection_id |
ftmississippistu |
language |
unknown |
topic |
Earth science geology marine geology machine learning geospatial geophysics |
spellingShingle |
Earth science geology marine geology machine learning geospatial geophysics Lee, Taylor Runyan A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
topic_facet |
Earth science geology marine geology machine learning geospatial geophysics |
description |
Seafloor properties, including total organic carbon (TOC) and the vertical thickness (isochores) of geological units, are sparsely measured on a global scale and spatial interpolation (prediction) techniques are often used as a proxy for observations. Previous geospatial interpolations of seafloor TOC exhibit gaps where little to no observed data exists. Recent machine learning techniques, based upon a suite of geophysical and geochemical properties (e.g., seafloor biomass, porosity, distance from coast) show promise in making globally complete, comprehensive, and statistically robust geospatial seafloor predictions. Here I apply a non-parametric (i.e., data-driven) machine learning (ML) algorithm, specifically k-nearest neighbors (kNN), to estimate the global distribution of seafloor TOC and marine isochores. This machine learning approach shows major advantages relative to geospatial interpolation, including results that are quantitative, easily updatable, accompanied with uncertainty estimation, and agnostic to spatial gaps in observations. Additionally. analysis of parameter space sample density provides a guide for future sampling. Resulting predictions of the global distribution of seafloor TOC and marine isochore thicknesses were used with ML workflow to predict other seafloor parameters (e.g., heat flow, temperature, salinity) in order to constrain the global distribution of the base of hydrate stability zone and methane generation for all sub-seafloor sediments. Estimating global carbon budgets is first-order dependent on accurate model input, therefore our estimate of the base of hydrate stability zone, and subsequent carbon and methane accumulation in the subseafloor yields improvement over the standard interpolation techniques used in previous global modeling analyses. By using these globally updateable machine learning parameters as the input to predictions, results provide easily updated global budgets of total carbon and methane generated. This dissertation presents valuable new global ... |
format |
Text |
author |
Lee, Taylor Runyan |
author_facet |
Lee, Taylor Runyan |
author_sort |
Lee, Taylor Runyan |
title |
A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
title_short |
A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
title_full |
A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
title_fullStr |
A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
title_full_unstemmed |
A machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
title_sort |
machine learning approach to predicting seafloor properties and their application in estimating a global methane hydrate inventory |
publisher |
Scholars Junction |
publishDate |
2021 |
url |
https://scholarsjunction.msstate.edu/td/5280 https://scholarsjunction.msstate.edu/context/td/article/6280/viewcontent/taylor_lee_dissertation.pdf |
genre |
Methane hydrate |
genre_facet |
Methane hydrate |
op_source |
Theses and Dissertations |
op_relation |
https://scholarsjunction.msstate.edu/td/5280 https://scholarsjunction.msstate.edu/context/td/article/6280/viewcontent/taylor_lee_dissertation.pdf |
_version_ |
1810456778262970368 |