{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-5331"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-5331","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Climate Insurance - Using Weather Data and AI to Manage Agricultural Risk in Developing Countries","abstract":"Weather index-based crop insurance has promised to be a lifeline for low-income farmers in developing countries. However, high-basis risk, high administration costs, and low willingness to pay have caused the demise of many pilot programs. Building onto the principles of index insurance we propose Climate Insurance, a new form of insurance based on predictive crop models that overcomes most of the primary objections of index insurance while achieving its goals of low administration costs, greatly reduced adverse selection, and the elimination of moral hazard. The crop model presented herein utilizes an artificial neural network to predict county- level yield per acre given only weather data for a growing season and the previous high yield. This model was developed using 93 years of historical NOAA weather and USDA corn yield data for 53 counties in Iowa, though we believe it to be fully transferrable to other locations and crops. It has an RMSE of only 12.47 for 2022 weather data and an RRMSE of 6.4%.","abstract_html":"Weather index-based crop insurance has promised to be a lifeline for low-income farmers in developing countries. However, high-basis risk, high administration costs, and low willingness to pay have caused the demise of many pilot programs. Building onto the principles of index insurance we propose Climate Insurance, a new form of insurance based on predictive crop models that overcomes most of the primary objections of index insurance while achieving its goals of low administration costs, greatly reduced adverse selection, and the elimination of moral hazard. The crop model presented herein utilizes an artificial neural network to predict county- level yield per acre given only weather data for a growing season and the previous high yield. This model was developed using 93 years of historical NOAA weather and USDA corn yield data for 53 counties in Iowa, though we believe it to be fully transferrable to other locations and crops. It has an RMSE of only 12.47 for 2022 weather data and an RRMSE of 6.4%.","abstract_has_math":false,"creators":["Denning, Scott A"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Economics","degree_department":null,"school":null,"contributors":["Dr. Matthew Lewis","Dr. Babur de Los Santos","Dr. Anastasia Thayer"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:31:26Z","subjects":["climate insurance","crop yield","yield prediction","predictive model","index insurance","Agricultural Economics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/4226","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/4226","record_label":"Repository record","record_kind":"record","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://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-5331","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Matthew Lewis","Dr. Babur de Los Santos","Dr. Anastasia Thayer"]},{"key":"dc:creator","label":"Author","values":["Denning, Scott A"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-05-31T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-05-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Economics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["climate insurance","crop yield","yield prediction","predictive model","index insurance","Agricultural Economics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/4226"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Weather index-based crop insurance has promised to be a lifeline for low-income farmers in developing countries. However, high-basis risk, high administration costs, and low willingness to pay have caused the demise of many pilot programs. Building onto the principles of index insurance we propose Climate Insurance, a new form of insurance based on predictive crop models that overcomes most of the primary objections of index insurance while achieving its goals of low administration costs, greatly reduced adverse selection, and the elimination of moral hazard. The crop model presented herein utilizes an artificial neural network to predict county- level yield per acre given only weather data for a growing season and the previous high yield. This model was developed using 93 years of historical NOAA weather and USDA corn yield data for 53 counties in Iowa, though we believe it to be fully transferrable to other locations and crops. It has an RMSE of only 12.47 for 2022 weather data and an RRMSE of 6.4%."]},{"key":"dc:title","label":"Title","values":["Climate Insurance - Using Weather Data and AI to Manage Agricultural Risk in Developing Countries"]}]}],"canonical_facts":{"dc:contributor":["Dr. Matthew Lewis","Dr. Babur de Los Santos","Dr. Anastasia Thayer"],"dc:creator":["Denning, Scott A"],"dc:date.available":["2025-05-31T07:00:00Z"],"dc:date.created":["2024-05-01T07:00:00Z"],"dc:description.abstract":["Weather index-based crop insurance has promised to be a lifeline for low-income farmers in developing countries. However, high-basis risk, high administration costs, and low willingness to pay have caused the demise of many pilot programs. Building onto the principles of index insurance we propose Climate Insurance, a new form of insurance based on predictive crop models that overcomes most of the primary objections of index insurance while achieving its goals of low administration costs, greatly reduced adverse selection, and the elimination of moral hazard. The crop model presented herein utilizes an artificial neural network to predict county- level yield per acre given only weather data for a growing season and the previous high yield. This model was developed using 93 years of historical NOAA weather and USDA corn yield data for 53 counties in Iowa, though we believe it to be fully transferrable to other locations and crops. It has an RMSE of only 12.47 for 2022 weather data and an RRMSE of 6.4%."],"dc:identifier":["https://open.clemson.edu/all_theses/4226"],"dc:subject":["climate insurance","crop yield","yield prediction","predictive model","index insurance","Agricultural Economics"],"dc:title":["Climate Insurance - Using Weather Data and AI to Manage Agricultural Risk in Developing Countries"],"thesis:degree_discipline":["Economics"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:31:26Z"}