A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain

Regolith, or unconsolidated materials overlying bedrock, exists as an active zone for many geological, geomorphological, hydrological and ecological processes. This zone and its processes are foundational to wide-ranging human needs and activities such as water supply, mineral exploration, forest ha...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shane Furze, Antóin M. O’Sullivan, Serge Allard, Toon Pronk, R. Allen Curry
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	bedrock regolith geomorphology Random Forest LiDAR modeling Science Q
Acceso en línea:	https://doaj.org/article/d7119edf4cdd47e7a0b82f819263e8ac
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d7119edf4cdd47e7a0b82f819263e8ac
record_format	dspace
spelling	oai:doaj.org-article:d7119edf4cdd47e7a0b82f819263e8ac2021-11-11T18:50:10ZA High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain10.3390/rs132142102072-4292https://doaj.org/article/d7119edf4cdd47e7a0b82f819263e8ac2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4210https://doaj.org/toc/2072-4292Regolith, or unconsolidated materials overlying bedrock, exists as an active zone for many geological, geomorphological, hydrological and ecological processes. This zone and its processes are foundational to wide-ranging human needs and activities such as water supply, mineral exploration, forest harvesting, agriculture, and engineered structures. Regolith thickness, or depth-to-bedrock (DTB), is typically unavailable or restricted to finer scale assessments because of the technical and cost limitations of traditional drilling, seismic, and ground-penetrating radar surveys. The objective of this study was to derive a high-resolution (10 m<sup>2</sup>) DTB model for the province of New Brunswick, Canada as a case study. This was accomplished by developing a DTB database from publicly available soil profiles, boreholes, drill holes, well logs, and outcrop transects (<i>n</i> = 203,238). A Random Forest model was produced by modeling the relationships between DTB measurements in the database to gridded datasets derived from both a LiDAR-derived digital elevation model and photo-interpreted surficial geology delineations. In developing the Random Forest model, DTB measurements were split 70:30 for model development and validation, respectively. The DTB model produced an <i>R</i><sup>2</sup> = 92.8%, <i>MAE</i> = 0.18 m, and <i>RMSE</i> = 0.61 m for the training, and an <i>R</i><sup>2</sup> = 80.3%, <i>MAE</i> = 0.18 m, and <i>RMSE</i> = 0.66 m for the validation data. This model provides an unprecedented resolution of DTB variance at a landscape scale. Additionally, the presented framework provides a fundamental understanding of regolith thickness across a post-glacial terrain, with potential application at the global scale.Shane FurzeAntóin M. O’SullivanSerge AllardToon PronkR. Allen CurryMDPI AGarticlebedrockregolithgeomorphologyRandom ForestLiDARmodelingScienceQENRemote Sensing, Vol 13, Iss 4210, p 4210 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	bedrock regolith geomorphology Random Forest LiDAR modeling Science Q
spellingShingle	bedrock regolith geomorphology Random Forest LiDAR modeling Science Q Shane Furze Antóin M. O’Sullivan Serge Allard Toon Pronk R. Allen Curry A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
description	Regolith, or unconsolidated materials overlying bedrock, exists as an active zone for many geological, geomorphological, hydrological and ecological processes. This zone and its processes are foundational to wide-ranging human needs and activities such as water supply, mineral exploration, forest harvesting, agriculture, and engineered structures. Regolith thickness, or depth-to-bedrock (DTB), is typically unavailable or restricted to finer scale assessments because of the technical and cost limitations of traditional drilling, seismic, and ground-penetrating radar surveys. The objective of this study was to derive a high-resolution (10 m<sup>2</sup>) DTB model for the province of New Brunswick, Canada as a case study. This was accomplished by developing a DTB database from publicly available soil profiles, boreholes, drill holes, well logs, and outcrop transects (<i>n</i> = 203,238). A Random Forest model was produced by modeling the relationships between DTB measurements in the database to gridded datasets derived from both a LiDAR-derived digital elevation model and photo-interpreted surficial geology delineations. In developing the Random Forest model, DTB measurements were split 70:30 for model development and validation, respectively. The DTB model produced an <i>R</i><sup>2</sup> = 92.8%, <i>MAE</i> = 0.18 m, and <i>RMSE</i> = 0.61 m for the training, and an <i>R</i><sup>2</sup> = 80.3%, <i>MAE</i> = 0.18 m, and <i>RMSE</i> = 0.66 m for the validation data. This model provides an unprecedented resolution of DTB variance at a landscape scale. Additionally, the presented framework provides a fundamental understanding of regolith thickness across a post-glacial terrain, with potential application at the global scale.
format	article
author	Shane Furze Antóin M. O’Sullivan Serge Allard Toon Pronk R. Allen Curry
author_facet	Shane Furze Antóin M. O’Sullivan Serge Allard Toon Pronk R. Allen Curry
author_sort	Shane Furze
title	A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
title_short	A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
title_full	A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
title_fullStr	A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
title_full_unstemmed	A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain
title_sort	high-resolution, random forest approach to mapping depth-to-bedrock across shallow overburden and post-glacial terrain
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d7119edf4cdd47e7a0b82f819263e8ac
work_keys_str_mv	AT shanefurze ahighresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT antoinmosullivan ahighresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT sergeallard ahighresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT toonpronk ahighresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT rallencurry ahighresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT shanefurze highresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT antoinmosullivan highresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT sergeallard highresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT toonpronk highresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain AT rallencurry highresolutionrandomforestapproachtomappingdepthtobedrockacrossshallowoverburdenandpostglacialterrain
_version_	1718431732020019200

A High-Resolution, Random Forest Approach to Mapping Depth-to-Bedrock across Shallow Overburden and Post-Glacial Terrain

Ejemplares similares