{"id":{"repo_id":"alabama","oai_identifier":"oai:ir.ua.edu:123456789/17031"},"canonical_url":"https://search.dev.ndltd.org/etd/alabama/oai:ir.ua.edu:123456789/17031","repository":{"repo_id":"alabama","name":"University of Alabama","base_url":"https://ir-api.ua.edu/oai/request"},"display":{"title":"Using Remote Sensing and Machine Learning to Improve County-Level Crop Yield Prediction in the Us Corn Belt","abstract":"The rapid increase in global population, coupled with the impacts of climate change, poses a significant threat to food security. Decisions related to the import and export of grains require detailed and timely information about potential crop yield. Therefore, accurate and timely crop yield prediction is crucial, as it provides essential insights to the stakeholders. Consequently, large-scale crop yield prediction has recently garnered considerable attention. Despite the advancements in crop yield prediction models, there are still several research gaps. First, most of the existing data-driven crop yield prediction models fail to account for the geographical variations in predictors. Second, many crop yield prediction models are developed for specific crops or regions. Third, most machine learning models for crop yield prediction remain confined to research settings and are rarely deployed online and used by stakeholders. This dissertation aims to address these gaps by developing machine learning models to improve county-level crop yield prediction. This dissertation consists of three manuscripts. The first manuscript uses a geographically weighted random forest regression (GWRFR) model to predict county-level corn yield, with a specific focus on addressing spatial heterogeneity. The second manuscript explores the transferability of deep learning models in crop yield prediction. The transfer learning framework used in this study can help in scenarios where a limited amount of data is available in the target domain. The third manuscript focuses on the deployment of deep learning models through a Web geographic information systems (GIS) application. This study presents a framework for delivering deep learning models online, enabling stakeholders to more conveniently use the models in county-level crop yield prediction to facilitate their decision-making.In summary, this dissertation augments existing approaches for crop yield prediction by integrating spatially explicit machine learning, deep transfer learning, and Web GIS. My research offers a comprehensive framework for using remote sensing and machine learning to improve county-level crop yield prediction. By improving prediction accuracy and model adaptability, this work supports more timely and informed decision-making in agriculture. Furthermore, by making the models publicly accessible, it enables broader use by stakeholders for crop yield prediction.","abstract_html":"The rapid increase in global population, coupled with the impacts of climate change, poses a significant threat to food security. Decisions related to the import and export of grains require detailed and timely information about potential crop yield. Therefore, accurate and timely crop yield prediction is crucial, as it provides essential insights to the stakeholders. Consequently, large-scale crop yield prediction has recently garnered considerable attention. Despite the advancements in crop yield prediction models, there are still several research gaps. First, most of the existing data-driven crop yield prediction models fail to account for the geographical variations in predictors. Second, many crop yield prediction models are developed for specific crops or regions. Third, most machine learning models for crop yield prediction remain confined to research settings and are rarely deployed online and used by stakeholders. This dissertation aims to address these gaps by developing machine learning models to improve county-level crop yield prediction. This dissertation consists of three manuscripts. The first manuscript uses a geographically weighted random forest regression (GWRFR) model to predict county-level corn yield, with a specific focus on addressing spatial heterogeneity. The second manuscript explores the transferability of deep learning models in crop yield prediction. The transfer learning framework used in this study can help in scenarios where a limited amount of data is available in the target domain. The third manuscript focuses on the deployment of deep learning models through a Web geographic information systems (GIS) application. This study presents a framework for delivering deep learning models online, enabling stakeholders to more conveniently use the models in county-level crop yield prediction to facilitate their decision-making.In summary, this dissertation augments existing approaches for crop yield prediction by integrating spatially explicit machine learning, deep transfer learning, and Web GIS. My research offers a comprehensive framework for using remote sensing and machine learning to improve county-level crop yield prediction. By improving prediction accuracy and model adaptability, this work supports more timely and informed decision-making in agriculture. Furthermore, by making the models publicly accessible, it enables broader use by stakeholders for crop yield prediction.","abstract_has_math":false,"creators":["Khan, Shahid Nawaz"],"institution":"University of Alabama Libraries","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Liu, Hongxing","Mungai, Leah","Maimaitijiang, Maitiniyazi","Zhang, Hankui"],"advisors":["Li, Dapeng"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-27T18:44:14Z","subjects":["crop yield prediction","deep learning","machine learning","remote sensing","spatial autocorrelation","transfer learning"],"languages":["en_US","English"],"rights":["All rights reserved by the author unless otherwise indicated."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1166310"],"render_values":[{"text":"1166310","href":null,"code":true}]}]},"links":{"outbound_url":"https://ir.ua.edu/handle/123456789/17031","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Liu, Hongxing","Mungai, Leah","Maimaitijiang, Maitiniyazi","Zhang, Hankui"]},{"key":"dc:contributor.advisor","label":"Advisor","values":["Li, Dapeng"]},{"key":"dc:creator","label":"Author","values":["Khan, Shahid Nawaz"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-04T16:14:41Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["8/27/2030"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher","label":"Institution","values":["University of Alabama Libraries"]},{"key":"dc:type","label":"Dc Type","values":["thesis","text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["crop yield prediction","deep learning","machine learning","remote sensing","spatial autocorrelation","transfer learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["All rights reserved by the author unless otherwise indicated."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1166310"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://ir.ua.edu/handle/123456789/17031"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Electronic Thesis or Dissertation"]},{"key":"dc:description.abstract","label":"Abstract","values":["The rapid increase in global population, coupled with the impacts of climate change, poses a significant threat to food security. Decisions related to the import and export of grains require detailed and timely information about potential crop yield. Therefore, accurate and timely crop yield prediction is crucial, as it provides essential insights to the stakeholders. Consequently, large-scale crop yield prediction has recently garnered considerable attention. Despite the advancements in crop yield prediction models, there are still several research gaps. First, most of the existing data-driven crop yield prediction models fail to account for the geographical variations in predictors. Second, many crop yield prediction models are developed for specific crops or regions. Third, most machine learning models for crop yield prediction remain confined to research settings and are rarely deployed online and used by stakeholders. This dissertation aims to address these gaps by developing machine learning models to improve county-level crop yield prediction. This dissertation consists of three manuscripts. The first manuscript uses a geographically weighted random forest regression (GWRFR) model to predict county-level corn yield, with a specific focus on addressing spatial heterogeneity. The second manuscript explores the transferability of deep learning models in crop yield prediction. The transfer learning framework used in this study can help in scenarios where a limited amount of data is available in the target domain. The third manuscript focuses on the deployment of deep learning models through a Web geographic information systems (GIS) application. This study presents a framework for delivering deep learning models online, enabling stakeholders to more conveniently use the models in county-level crop yield prediction to facilitate their decision-making.In summary, this dissertation augments existing approaches for crop yield prediction by integrating spatially explicit machine learning, deep transfer learning, and Web GIS. My research offers a comprehensive framework for using remote sensing and machine learning to improve county-level crop yield prediction. By improving prediction accuracy and model adaptability, this work supports more timely and informed decision-making in agriculture. Furthermore, by making the models publicly accessible, it enables broader use by stakeholders for crop yield prediction."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["electronic"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Using Remote Sensing and Machine Learning to Improve County-Level Crop Yield Prediction in the Us Corn Belt"]}]}],"canonical_facts":{"dc:contributor":["Liu, Hongxing","Mungai, Leah","Maimaitijiang, Maitiniyazi","Zhang, Hankui"],"dc:contributor.advisor":["Li, Dapeng"],"dc:creator":["Khan, Shahid Nawaz"],"dc:date.accessioned":["2025-09-04T16:14:41Z"],"dc:date.available":["8/27/2030"],"dc:date.issued":["2025"],"dc:description":["Electronic Thesis or Dissertation"],"dc:description.abstract":["The rapid increase in global population, coupled with the impacts of climate change, poses a significant threat to food security. Decisions related to the import and export of grains require detailed and timely information about potential crop yield. Therefore, accurate and timely crop yield prediction is crucial, as it provides essential insights to the stakeholders. Consequently, large-scale crop yield prediction has recently garnered considerable attention. Despite the advancements in crop yield prediction models, there are still several research gaps. First, most of the existing data-driven crop yield prediction models fail to account for the geographical variations in predictors. Second, many crop yield prediction models are developed for specific crops or regions. Third, most machine learning models for crop yield prediction remain confined to research settings and are rarely deployed online and used by stakeholders. This dissertation aims to address these gaps by developing machine learning models to improve county-level crop yield prediction. This dissertation consists of three manuscripts. The first manuscript uses a geographically weighted random forest regression (GWRFR) model to predict county-level corn yield, with a specific focus on addressing spatial heterogeneity. The second manuscript explores the transferability of deep learning models in crop yield prediction. The transfer learning framework used in this study can help in scenarios where a limited amount of data is available in the target domain. The third manuscript focuses on the deployment of deep learning models through a Web geographic information systems (GIS) application. This study presents a framework for delivering deep learning models online, enabling stakeholders to more conveniently use the models in county-level crop yield prediction to facilitate their decision-making.In summary, this dissertation augments existing approaches for crop yield prediction by integrating spatially explicit machine learning, deep transfer learning, and Web GIS. My research offers a comprehensive framework for using remote sensing and machine learning to improve county-level crop yield prediction. By improving prediction accuracy and model adaptability, this work supports more timely and informed decision-making in agriculture. Furthermore, by making the models publicly accessible, it enables broader use by stakeholders for crop yield prediction."],"dc:format.medium":["electronic"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["1166310"],"dc:identifier.uri":["https://ir.ua.edu/handle/123456789/17031"],"dc:language":["English"],"dc:language.iso":["en_US"],"dc:publisher":["University of Alabama Libraries"],"dc:rights":["All rights reserved by the author unless otherwise indicated."],"dc:subject":["crop yield prediction","deep learning","machine learning","remote sensing","spatial autocorrelation","transfer learning"],"dc:title":["Using Remote Sensing and Machine Learning to Improve County-Level Crop Yield Prediction in the Us Corn Belt"],"dc:type":["thesis","text"]},"updated_at":"2026-07-27T18:44:14Z"}