{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53194"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53194","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"EVALUATING ANNUAL LANDSAT-BASED IRRIGATION MAPS FOR FIT-FOR-PURPOSE USE : AGREEMENT, DISAGREEMENT, AND MODEL SENSITIVITY IN THE CONTIGUOUS UNITED STATES","abstract":"Thesis (M.S.)--Michigan State University. Geological Sciences - Master of Science, 2026","abstract_html":"Thesis (M.S.)--Michigan State University. Geological Sciences - Master of Science, 2026","abstract_has_math":false,"creators":["Rapp, Jeremy"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Kendall, Anthony D","Hyndman, David W","Henebry, Geoffrey M"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:41Z","subjects":["Hydrologic sciences","Remote sensing","Hydrology"],"languages":["eng"],"rights":["Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53194","local:Rapp_grad.msu_0128N_22252"],"render_values":[{"text":"etd:53194","href":null,"code":true},{"text":"local:Rapp_grad.msu_0128N_22252","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/prc9-8b30","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/prc9-8b30","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://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53194","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kendall, Anthony D","Hyndman, David W","Henebry, Geoffrey M"]},{"key":"dc:creator","label":"Author","values":["Rapp, Jeremy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hydrologic sciences","Remote sensing","Hydrology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53194","local:Rapp_grad.msu_0128N_22252","https://doi.org/doi:10.25335/prc9-8b30"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M.S.)--Michigan State University. Geological Sciences - Master of Science, 2026","Irrigation is one of the major ways humans alter the terrestrial water cycle, but mapping it is not the same as observing a land-cover class. It is a management action inferred from vegetation condition, climate, field geometry, training data, and model assumptions. Annual Landsat-based irrigation products are therefore spatial predictions of likely irrigation, not direct measurements of water application.Chapter 2 compares AIM-HPA, LANID, and IrrMapper v1.2 within their shared overlap along the western High Plains Aquifer. The chapter evaluates mapped area, pixel overlap, crop composition, and patch geometry rather than treating any product as the correct map. The products show similar regional behavior but do not map identical pixels. Some disagreement reflects differences in domain, training data, masking, model deployment, and use of the USDA Census of Agriculture, which is useful but not annual spatial ground truth. Chapter 3 tests a CONUS-scale XGBoost workflow using multi-source training data, Google Earth Engine feature generation, local tiled inference, and hard-negative mining. The final model reduced overprediction in humid Michigan but remained conservative in California and the High Plains. The thesis identifies where irrigation maps are stable enough for use and where inference remains sensitive to model design, input data, crop system, observational support, and benchmark choice.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (161 p.) : ill."]},{"key":"dc:title","label":"Title","values":["EVALUATING ANNUAL LANDSAT-BASED IRRIGATION MAPS FOR FIT-FOR-PURPOSE USE : AGREEMENT, DISAGREEMENT, AND MODEL SENSITIVITY IN THE CONTIGUOUS UNITED STATES"]}]}],"canonical_facts":{"dc:contributor":["Kendall, Anthony D","Hyndman, David W","Henebry, Geoffrey M"],"dc:creator":["Rapp, Jeremy"],"dc:date":["2026"],"dc:description":["Thesis (M.S.)--Michigan State University. Geological Sciences - Master of Science, 2026","Irrigation is one of the major ways humans alter the terrestrial water cycle, but mapping it is not the same as observing a land-cover class. It is a management action inferred from vegetation condition, climate, field geometry, training data, and model assumptions. Annual Landsat-based irrigation products are therefore spatial predictions of likely irrigation, not direct measurements of water application.Chapter 2 compares AIM-HPA, LANID, and IrrMapper v1.2 within their shared overlap along the western High Plains Aquifer. The chapter evaluates mapped area, pixel overlap, crop composition, and patch geometry rather than treating any product as the correct map. The products show similar regional behavior but do not map identical pixels. Some disagreement reflects differences in domain, training data, masking, model deployment, and use of the USDA Census of Agriculture, which is useful but not annual spatial ground truth. Chapter 3 tests a CONUS-scale XGBoost workflow using multi-source training data, Google Earth Engine feature generation, local tiled inference, and hard-negative mining. The final model reduced overprediction in humid Michigan but remained conservative in California and the High Plains. The thesis identifies where irrigation maps are stable enough for use and where inference remains sensitive to model design, input data, crop system, observational support, and benchmark choice.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (161 p.) : ill."],"dc:identifier":["etd:53194","local:Rapp_grad.msu_0128N_22252","https://doi.org/doi:10.25335/prc9-8b30"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution 4.0 International"],"dc:subject":["Hydrologic sciences","Remote sensing","Hydrology"],"dc:title":["EVALUATING ANNUAL LANDSAT-BASED IRRIGATION MAPS FOR FIT-FOR-PURPOSE USE : AGREEMENT, DISAGREEMENT, AND MODEL SENSITIVITY IN THE CONTIGUOUS UNITED STATES"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:41Z"}