{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/140899"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/140899","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Why Are Some Watersheds More Sediment-Productive Than Others? An Explainable AI Approach","abstract":"The Sediment Delivery Ratio (SDR) represents the proportion of eroded sediment within a watershed that ultimately reaches its outlet. Sediment yield (SY) is defined as the amount of sediment exported from a watershed outlet per unit time, normalized by drainage area. Quantifying the spatial variability of both metrics is critical for sediment management and water quality protection, yet the drivers of SDR remain poorly constrained at continental scales. Here, we develop a data-driven framework to model SDR and SY across the contiguous United States (CONUS) by integrating high-frequency aquatic sensing, sediment load estimation, and explainable machine learning. SY and SDR were quantified at 134 U.S. Geological Survey (USGS) stations and modeled using a random forest algorithm trained on 20 basin attributes, spanning climate, land cover, soils and geology, and topography. The model performed well in the estimation of SY and SDR, yielding R2 values of 0.59 and 0.60, respectively. Model interpretation using Shapley values revealed that anthropogenic factors—including urban area, pasture area, and road density—exert stronger controls on SDR than natural drivers such as slope or precipitation, while the opposite relationship was observed for SY, where natural drivers prevailed over anthropogenic factors. We extended the model to the spatial variability of SY and SDR in two basins of major interest (the Upper Mississippi River Basin and the Chesapeake Bay Basin), identifying highly connected and productive basins to be targeted for management intervention. This study provides a large-scale, explainable framework for predicting SDR and SY using remote sensing and watershed attributes, offering new insights into the spatial controls of sediment delivery and supporting the design of targeted sediment mitigation strategies across heterogeneous landscapes.","abstract_html":"The Sediment Delivery Ratio (SDR) represents the proportion of eroded sediment within a watershed that ultimately reaches its outlet. Sediment yield (SY) is defined as the amount of sediment exported from a watershed outlet per unit time, normalized by drainage area. Quantifying the spatial variability of both metrics is critical for sediment management and water quality protection, yet the drivers of SDR remain poorly constrained at continental scales. Here, we develop a data-driven framework to model SDR and SY across the contiguous United States (CONUS) by integrating high-frequency aquatic sensing, sediment load estimation, and explainable machine learning. SY and SDR were quantified at 134 U.S. Geological Survey (USGS) stations and modeled using a random forest algorithm trained on 20 basin attributes, spanning climate, land cover, soils and geology, and topography. The model performed well in the estimation of SY and SDR, yielding R2 values of 0.59 and 0.60, respectively. Model interpretation using Shapley values revealed that anthropogenic factors—including urban area, pasture area, and road density—exert stronger controls on SDR than natural drivers such as slope or precipitation, while the opposite relationship was observed for SY, where natural drivers prevailed over anthropogenic factors. We extended the model to the spatial variability of SY and SDR in two basins of major interest (the Upper Mississippi River Basin and the Chesapeake Bay Basin), identifying highly connected and productive basins to be targeted for management intervention. This study provides a large-scale, explainable framework for predicting SDR and SY using remote sensing and watershed attributes, offering new insights into the spatial controls of sediment delivery and supporting the design of targeted sediment mitigation strategies across heterogeneous landscapes.","abstract_has_math":false,"creators":["Shrestha, Sugam"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Civil Engineering","degree_department":"Civil and Environmental Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Husic, Admin"],"committee_members":["Strom, Kyle Brent","Stewart, Ryan D."],"year":2026,"date_issued":"2026-01-20","date_published":"2026-01-20","updated_at":"2026-07-22T22:20:07Z","subjects":["Sediment yield","Sediment delivery ratio","High frequency sensors","Turbidity","explainable AI","targeted mitigation"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45436"],"render_values":[{"text":"vt_gsexam:45436","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/140899","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Husic, Admin"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Strom, Kyle Brent","Stewart, Ryan D."]},{"key":"dc:contributor.department","label":"Department","values":["Civil and Environmental Engineering"]},{"key":"dc:creator","label":"Author","values":["Shrestha, Sugam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-21T09:00:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-21T09:00:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-01-20"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Civil Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Sediment yield","Sediment delivery ratio","High frequency sensors","Turbidity","explainable AI","targeted mitigation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45436"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/140899"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The Sediment Delivery Ratio (SDR) represents the proportion of eroded sediment within a watershed that ultimately reaches its outlet. Sediment yield (SY) is defined as the amount of sediment exported from a watershed outlet per unit time, normalized by drainage area. Quantifying the spatial variability of both metrics is critical for sediment management and water quality protection, yet the drivers of SDR remain poorly constrained at continental scales. Here, we develop a data-driven framework to model SDR and SY across the contiguous United States (CONUS) by integrating high-frequency aquatic sensing, sediment load estimation, and explainable machine learning. SY and SDR were quantified at 134 U.S. Geological Survey (USGS) stations and modeled using a random forest algorithm trained on 20 basin attributes, spanning climate, land cover, soils and geology, and topography. The model performed well in the estimation of SY and SDR, yielding R2 values of 0.59 and 0.60, respectively. Model interpretation using Shapley values revealed that anthropogenic factors—including urban area, pasture area, and road density—exert stronger controls on SDR than natural drivers such as slope or precipitation, while the opposite relationship was observed for SY, where natural drivers prevailed over anthropogenic factors. We extended the model to the spatial variability of SY and SDR in two basins of major interest (the Upper Mississippi River Basin and the Chesapeake Bay Basin), identifying highly connected and productive basins to be targeted for management intervention. This study provides a large-scale, explainable framework for predicting SDR and SY using remote sensing and watershed attributes, offering new insights into the spatial controls of sediment delivery and supporting the design of targeted sediment mitigation strategies across heterogeneous landscapes."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Sediment washed from land into rivers can harm water quality, overwhelm reservoirs, and worsen flooding, yet not all eroded soil actually reaches a watershed's outlet. To better understand what controls how much sediment is produced and delivered, we combined high-frequency monitoring from U.S. Geological Survey stations with watershed characteristics and machine learning to estimate sediment yield and sediment delivery ratio across the contiguous United States. Our results show that natural factors like climate and topography largely determine how much sediment is generated, while human activities such as urban development, pasture land, and road networks have a stronger influence on how efficiently that sediment reaches streams. Applying this approach to the Upper Mississippi and Chesapeake Bay basins identified key areas where sediment sources and transport connectivity are high, offering guidance for targeted management to protect water quality."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Why Are Some Watersheds More Sediment-Productive Than Others? An Explainable AI Approach"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Husic, Admin"],"dc:contributor.committeemember":["Strom, Kyle Brent","Stewart, Ryan D."],"dc:contributor.department":["Civil and Environmental Engineering"],"dc:creator":["Shrestha, Sugam"],"dc:date.accessioned":["2026-01-21T09:00:35Z"],"dc:date.available":["2026-01-21T09:00:35Z"],"dc:date.issued":["2026-01-20"],"dc:description.abstract":["The Sediment Delivery Ratio (SDR) represents the proportion of eroded sediment within a watershed that ultimately reaches its outlet. Sediment yield (SY) is defined as the amount of sediment exported from a watershed outlet per unit time, normalized by drainage area. Quantifying the spatial variability of both metrics is critical for sediment management and water quality protection, yet the drivers of SDR remain poorly constrained at continental scales. Here, we develop a data-driven framework to model SDR and SY across the contiguous United States (CONUS) by integrating high-frequency aquatic sensing, sediment load estimation, and explainable machine learning. SY and SDR were quantified at 134 U.S. Geological Survey (USGS) stations and modeled using a random forest algorithm trained on 20 basin attributes, spanning climate, land cover, soils and geology, and topography. The model performed well in the estimation of SY and SDR, yielding R2 values of 0.59 and 0.60, respectively. Model interpretation using Shapley values revealed that anthropogenic factors—including urban area, pasture area, and road density—exert stronger controls on SDR than natural drivers such as slope or precipitation, while the opposite relationship was observed for SY, where natural drivers prevailed over anthropogenic factors. We extended the model to the spatial variability of SY and SDR in two basins of major interest (the Upper Mississippi River Basin and the Chesapeake Bay Basin), identifying highly connected and productive basins to be targeted for management intervention. This study provides a large-scale, explainable framework for predicting SDR and SY using remote sensing and watershed attributes, offering new insights into the spatial controls of sediment delivery and supporting the design of targeted sediment mitigation strategies across heterogeneous landscapes."],"dc:description.abstractgeneral":["Sediment washed from land into rivers can harm water quality, overwhelm reservoirs, and worsen flooding, yet not all eroded soil actually reaches a watershed's outlet. To better understand what controls how much sediment is produced and delivered, we combined high-frequency monitoring from U.S. Geological Survey stations with watershed characteristics and machine learning to estimate sediment yield and sediment delivery ratio across the contiguous United States. Our results show that natural factors like climate and topography largely determine how much sediment is generated, while human activities such as urban development, pasture land, and road networks have a stronger influence on how efficiently that sediment reaches streams. Applying this approach to the Upper Mississippi and Chesapeake Bay basins identified key areas where sediment sources and transport connectivity are high, offering guidance for targeted management to protect water quality."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:45436"],"dc:identifier.uri":["https://hdl.handle.net/10919/140899"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Sediment yield","Sediment delivery ratio","High frequency sensors","Turbidity","explainable AI","targeted mitigation"],"dc:title":["Why Are Some Watersheds More Sediment-Productive Than Others? An Explainable AI Approach"],"dc:type":["Thesis"],"thesis:degree_discipline":["Civil Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:07Z"}