{"id":{"repo_id":"marshall","oai_identifier":"oai:mds.marshall.edu:etd-1259"},"canonical_url":"https://search.ndltd.org/etd/marshall/oai:mds.marshall.edu:etd-1259","repository":{"repo_id":"marshall","name":"Marshall University","base_url":"https://mds.marshall.edu/do/oai/"},"display":{"title":"The Detection of Forest Structures in the Monongahela National Forest Using LiDAR","abstract":"The mapping of structural elements of a forest is important for forestry management to provide a baseline for old and new-growth trees while providing height strata for a stand. These activities are important for the overall monitoring process which aids in the understanding of anthropogenic and natural disturbances. Height information recorded for each discrete point is key for the creation of canopy height, canopy surface, and canopy cover models. The aim of this study is to assess if LiDAR can be used to determine forest structures. Small footprint, leaf-off LiDAR data were obtained for the Monongahela National Forest, West Virginia. This dataset was compared to Landsat imagery acquired for the same area. Each dataset endured supervised classifications and object oriented segmentation with random forest classifications. These approaches took into account derived variables such as, percentages of canopy height, canopy cover, stem density, and normalized difference vegetation index, which were converted from the original datasets. Evaluation of the study depicted that the classification of the Landsat data produced results ranging between 31.3 and 50.2%, whilst the LiDAR dataset produced accuracies ranging from 54.7 to 80.1%. The results of this study increase the potential of LiDAR to be used regularly as a forestry management technique and warrant future research.","abstract_html":"The mapping of structural elements of a forest is important for forestry management to provide a baseline for old and new-growth trees while providing height strata for a stand. These activities are important for the overall monitoring process which aids in the understanding of anthropogenic and natural disturbances. Height information recorded for each discrete point is key for the creation of canopy height, canopy surface, and canopy cover models. The aim of this study is to assess if LiDAR can be used to determine forest structures. Small footprint, leaf-off LiDAR data were obtained for the Monongahela National Forest, West Virginia. This dataset was compared to Landsat imagery acquired for the same area. Each dataset endured supervised classifications and object oriented segmentation with random forest classifications. These approaches took into account derived variables such as, percentages of canopy height, canopy cover, stem density, and normalized difference vegetation index, which were converted from the original datasets. Evaluation of the study depicted that the classification of the Landsat data produced results ranging between 31.3 and 50.2%, whilst the LiDAR dataset produced accuracies ranging from 54.7 to 80.1%. The results of this study increase the potential of LiDAR to be used regularly as a forestry management technique and warrant future research.","abstract_has_math":false,"creators":["Norman, Dominique"],"institution":null,"degree_name":"Geography","degree_level":"Thesis","degree_discipline":"College of Liberal Arts","degree_department":null,"school":null,"contributors":["Anita Walz","Godwin Djietror","Min Kook Kim"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-21T19:55:54Z","subjects":["Forest Management","Forest Sciences","Geography","Life Sciences","Nature and Society Relations","Physical and Environmental Geography","Social and Behavioral Sciences","Landsat","Lidar","Monongahelia National Forest","Object Oriented","Random Forest","Remote Sensing"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://mds.marshall.edu/etd/258","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://mds.marshall.edu/etd/258","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://mds.marshall.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Amds.marshall.edu%3Aetd-1259","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Anita Walz","Godwin Djietror","Min Kook Kim"]},{"key":"dc:creator","label":"Author","values":["Norman, Dominique"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2012-06-07T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2012-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["College of Liberal Arts"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Geography"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Forest Management","Forest Sciences","Geography","Life Sciences","Nature and Society Relations","Physical and Environmental Geography","Social and Behavioral Sciences","Landsat","Lidar","Monongahelia National Forest","Object Oriented","Random Forest","Remote Sensing"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://mds.marshall.edu/etd/258"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The mapping of structural elements of a forest is important for forestry management to provide a baseline for old and new-growth trees while providing height strata for a stand. These activities are important for the overall monitoring process which aids in the understanding of anthropogenic and natural disturbances. Height information recorded for each discrete point is key for the creation of canopy height, canopy surface, and canopy cover models. The aim of this study is to assess if LiDAR can be used to determine forest structures. Small footprint, leaf-off LiDAR data were obtained for the Monongahela National Forest, West Virginia. This dataset was compared to Landsat imagery acquired for the same area. Each dataset endured supervised classifications and object oriented segmentation with random forest classifications. These approaches took into account derived variables such as, percentages of canopy height, canopy cover, stem density, and normalized difference vegetation index, which were converted from the original datasets. Evaluation of the study depicted that the classification of the Landsat data produced results ranging between 31.3 and 50.2%, whilst the LiDAR dataset produced accuracies ranging from 54.7 to 80.1%. The results of this study increase the potential of LiDAR to be used regularly as a forestry management technique and warrant future research."]},{"key":"dc:title","label":"Title","values":["The Detection of Forest Structures in the Monongahela National Forest Using LiDAR"]}]}],"canonical_facts":{"dc:contributor":["Anita Walz","Godwin Djietror","Min Kook Kim"],"dc:creator":["Norman, Dominique"],"dc:date.available":["2012-06-07T07:00:00Z"],"dc:date.created":["2012-01-01T08:00:00Z"],"dc:description.abstract":["The mapping of structural elements of a forest is important for forestry management to provide a baseline for old and new-growth trees while providing height strata for a stand. These activities are important for the overall monitoring process which aids in the understanding of anthropogenic and natural disturbances. Height information recorded for each discrete point is key for the creation of canopy height, canopy surface, and canopy cover models. The aim of this study is to assess if LiDAR can be used to determine forest structures. Small footprint, leaf-off LiDAR data were obtained for the Monongahela National Forest, West Virginia. This dataset was compared to Landsat imagery acquired for the same area. Each dataset endured supervised classifications and object oriented segmentation with random forest classifications. These approaches took into account derived variables such as, percentages of canopy height, canopy cover, stem density, and normalized difference vegetation index, which were converted from the original datasets. Evaluation of the study depicted that the classification of the Landsat data produced results ranging between 31.3 and 50.2%, whilst the LiDAR dataset produced accuracies ranging from 54.7 to 80.1%. The results of this study increase the potential of LiDAR to be used regularly as a forestry management technique and warrant future research."],"dc:identifier":["https://mds.marshall.edu/etd/258"],"dc:subject":["Forest Management","Forest Sciences","Geography","Life Sciences","Nature and Society Relations","Physical and Environmental Geography","Social and Behavioral Sciences","Landsat","Lidar","Monongahelia National Forest","Object Oriented","Random Forest","Remote Sensing"],"dc:title":["The Detection of Forest Structures in the Monongahela National Forest Using LiDAR"],"thesis:degree_discipline":["College of Liberal Arts"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Geography"]},"updated_at":"2026-11-21T19:55:54Z"}