{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53044"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53044","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"MACHINE LEARNING APPROACH FOR GAP FILLING, PREDICTION, AND SENSOR OPTIMIZATION IN IOT-BASED AGRICULTURAL SYSTEMS","abstract":"Thesis (M.S.)--Michigan State University. Biosystems Engineering - Master of Science, 2026","abstract_html":"Thesis (M.S.)--Michigan State University. Biosystems Engineering - Master of Science, 2026","abstract_has_math":false,"creators":["Rana, Shivani"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Dong, Younsuk","Yi, Jiyoon","Cao, Zhichao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:37Z","subjects":["Agricultural engineering"],"languages":["eng"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53044","local:Rana_grad.msu_0128N_22050"],"render_values":[{"text":"etd:53044","href":null,"code":true},{"text":"local:Rana_grad.msu_0128N_22050","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/ap0b-j811","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/ap0b-j811","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_53044","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dong, Younsuk","Yi, Jiyoon","Cao, Zhichao"]},{"key":"dc:creator","label":"Author","values":["Rana, Shivani"]}]},{"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":["Agricultural engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53044","local:Rana_grad.msu_0128N_22050","https://doi.org/doi:10.25335/ap0b-j811"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M.S.)--Michigan State University. Biosystems Engineering - Master of Science, 2026","Internet of Things (IoT) systems enable continuous real-time crop monitoring, supporting sustainable agricultural practices. However, challenges like sensor failures, data gaps, and high material cost limit their scalability. This study explores machine learning frameworks for restoring gaps in leaf wetness data, estimating multi-depth soil moisture, and optimizing sensor deployment. Predictive models learn temporal patterns by capturing nonlinear complex interactions between plant and climatic variables. Study shows hybrid gap-filling models improved the prediction accuracy by combining complementary strengths of individual machine learning (ML) algorithms. ML models also successfully captured soil moisture dynamics when adjacent-depth soil moisture measurement is included, but accuracy decline sharply when solely environmental variables is used for prediction, indicating the dominance influence of neighboring soil-moisture conditions.Finally, research proposed a diameter-based reference tree scaling method to correct the magnitude differences in sap flow estimates that arise from structural variation across trees. Scaling had pronounced effect on structurally dissimilar trees (diameter based), by increasing R2 from 0.89 to 0.93, while reducing error and bias (Mean Absolute Error (MAE) : 9.27 to 8.78; Root Mean Square Error (RMSE): 15.75 to 13.33; Bias: − 0.62 to 0.58). In contrast, similar trees have minimal scaling effect due to inherently synchronized responses, allowing raw transfer without adjustment. Overall, this research provides insights on data-driven approach for improving data quality, predictive capability and sensor optimization in IoT based agricultural applications.","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 (155 p.) : ill."]},{"key":"dc:title","label":"Title","values":["MACHINE LEARNING APPROACH FOR GAP FILLING, PREDICTION, AND SENSOR OPTIMIZATION IN IOT-BASED AGRICULTURAL SYSTEMS"]}]}],"canonical_facts":{"dc:contributor":["Dong, Younsuk","Yi, Jiyoon","Cao, Zhichao"],"dc:creator":["Rana, Shivani"],"dc:date":["2026"],"dc:description":["Thesis (M.S.)--Michigan State University. Biosystems Engineering - Master of Science, 2026","Internet of Things (IoT) systems enable continuous real-time crop monitoring, supporting sustainable agricultural practices. However, challenges like sensor failures, data gaps, and high material cost limit their scalability. This study explores machine learning frameworks for restoring gaps in leaf wetness data, estimating multi-depth soil moisture, and optimizing sensor deployment. Predictive models learn temporal patterns by capturing nonlinear complex interactions between plant and climatic variables. Study shows hybrid gap-filling models improved the prediction accuracy by combining complementary strengths of individual machine learning (ML) algorithms. ML models also successfully captured soil moisture dynamics when adjacent-depth soil moisture measurement is included, but accuracy decline sharply when solely environmental variables is used for prediction, indicating the dominance influence of neighboring soil-moisture conditions.Finally, research proposed a diameter-based reference tree scaling method to correct the magnitude differences in sap flow estimates that arise from structural variation across trees. Scaling had pronounced effect on structurally dissimilar trees (diameter based), by increasing R2 from 0.89 to 0.93, while reducing error and bias (Mean Absolute Error (MAE) : 9.27 to 8.78; Root Mean Square Error (RMSE): 15.75 to 13.33; Bias: − 0.62 to 0.58). In contrast, similar trees have minimal scaling effect due to inherently synchronized responses, allowing raw transfer without adjustment. Overall, this research provides insights on data-driven approach for improving data quality, predictive capability and sensor optimization in IoT based agricultural applications.","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 (155 p.) : ill."],"dc:identifier":["etd:53044","local:Rana_grad.msu_0128N_22050","https://doi.org/doi:10.25335/ap0b-j811"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Agricultural engineering"],"dc:title":["MACHINE LEARNING APPROACH FOR GAP FILLING, PREDICTION, AND SENSOR OPTIMIZATION IN IOT-BASED AGRICULTURAL SYSTEMS"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:37Z"}