{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2961"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2961","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"ABOVEGROUND BIOMASS DENSITY ESTIMATION USING DEEP LEARNING: INSIGHT FROM NEON GROUND-TRUTH DATA AND SIMULATED GEDI WAVEFORM","abstract":"Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models.","abstract_html":"Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth&#x27;s carbon cycle and informing climate strategies. NASA&#x27;s GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models.","abstract_has_math":false,"creators":["Mahaur, Ashish"],"institution":null,"degree_name":"Master of Science in Integrated Geospatial Technology (MS)","degree_level":"Open Access Master's Thesis","degree_discipline":"Department of Civil, Environmental, and Geospatial Engineering","degree_department":null,"school":null,"contributors":["Tao Liu","Jae Sung Kim"],"advisors":[],"committee_chairs":[],"committee_members":["Parth Parimalbhai Bhatt"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:19:12Z","subjects":["Aboveground Biomass","AGBD","NEON","Simulated GEDI Waveform","Deep Learning","Machine Learning","Forest Management","Physical and Environmental Geography","Remote Sensing","Spatial Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1861"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1861","href":"https://digitalcommons.mtu.edu/etdr/1861","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1861","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1861","record_label":"Repository record","record_kind":"doi","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://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2961","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Tao Liu","Jae Sung Kim"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Parth Parimalbhai Bhatt"]},{"key":"dc:creator","label":"Author","values":["Mahaur, Ashish"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2024-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Civil, Environmental, and Geospatial Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Open Access Master's Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Integrated Geospatial Technology (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Aboveground Biomass","AGBD","NEON","Simulated GEDI Waveform","Deep Learning","Machine Learning","Forest Management","Physical and Environmental Geography","Remote Sensing","Spatial Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1861","https://digitalcommons.mtu.edu/etdr/1861"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models."]},{"key":"dc:title","label":"Title","values":["ABOVEGROUND BIOMASS DENSITY ESTIMATION USING DEEP LEARNING: INSIGHT FROM NEON GROUND-TRUTH DATA AND SIMULATED GEDI WAVEFORM"]}]}],"canonical_facts":{"dc:contributor":["Tao Liu","Jae Sung Kim"],"dc:contributor.committeemember":["Parth Parimalbhai Bhatt"],"dc:creator":["Mahaur, Ashish"],"dc:date.created":["2024-01-01T08:00:00Z"],"dc:description.abstract":["Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models."],"dc:identifier":["10.37099/mtu.dc.etdr/1861","https://digitalcommons.mtu.edu/etdr/1861"],"dc:subject":["Aboveground Biomass","AGBD","NEON","Simulated GEDI Waveform","Deep Learning","Machine Learning","Forest Management","Physical and Environmental Geography","Remote Sensing","Spatial Science"],"dc:title":["ABOVEGROUND BIOMASS DENSITY ESTIMATION USING DEEP LEARNING: INSIGHT FROM NEON GROUND-TRUTH DATA AND SIMULATED GEDI WAVEFORM"],"thesis:degree_discipline":["Department of Civil, Environmental, and Geospatial Engineering"],"thesis:degree_level":["Open Access Master's Thesis"],"thesis:degree_name":["Master of Science in Integrated Geospatial Technology (MS)"]},"updated_at":"2026-11-19T08:19:12Z"}