{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9498"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9498","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"On Predicting Omnidirectional Honey Bee Traffic Using Weather and Electromagnetic Radiation","abstract":"Honey bees are responsible for pollinating many important crops in the United States. However, honey bee populations have declined significantly since 1961. While some causes of this decline are known, others are not. By utilizing electronic bee hive monitoring (EBM) systems, bee keepers and researchers have an added resource in determining the causes of these declines so that the issues can be remedied. For nearly five months (May through October) during the 2020 honey bee foraging season in Logan, Utah, USA, we collected on-site weather and electromagnetic radiation (EMR) readings and videos of the hive entrances of six bee hives every 15 minutes. Each video was processed to estimate the number of bee motions, and the bee motion counts were paired with the weather and EMR data. We show that an algorithm consisting of many decision trees in concert (called a random forest regressor) can be used to accurately predict bee motion counts from one moment to another. By using specific weather variables coupled with omnidirectional bee motion counts, we demonstrate that 54.7% of bee motion at the hive entrance can be predicted accurately with data records spaced 15 minutes apart, and 88.6% of the bee motion can be predicted accurately for those 15 minute measurements averaged over 12 hours. We suggest that these predictions can be used to trigger remote alerts for bee keepers when the observed behavior significantly differs from the predicted values. We also propose that the nine-hour relative humidity trend is a major predictor variable in addition to solar radiation and temperature. Additionally, we show that nearly 19% of the changes in bee motion at the hive entrance can be explained by the changes in select EMR variables. In conjunction with these findings, we contribute the design and software for our Weather and EMR Sensing Station, along with 12 curated data files to the public for further exploration. We also discuss various correlations, relations, and observations pertaining to variables that may be influencing bee behavior. The associated expenses of this research was approximately 1,500 US dollars.","abstract_html":"Honey bees are responsible for pollinating many important crops in the United States. However, honey bee populations have declined significantly since 1961. While some causes of this decline are known, others are not. By utilizing electronic bee hive monitoring (EBM) systems, bee keepers and researchers have an added resource in determining the causes of these declines so that the issues can be remedied. For nearly five months (May through October) during the 2020 honey bee foraging season in Logan, Utah, USA, we collected on-site weather and electromagnetic radiation (EMR) readings and videos of the hive entrances of six bee hives every 15 minutes. Each video was processed to estimate the number of bee motions, and the bee motion counts were paired with the weather and EMR data. We show that an algorithm consisting of many decision trees in concert (called a random forest regressor) can be used to accurately predict bee motion counts from one moment to another. By using specific weather variables coupled with omnidirectional bee motion counts, we demonstrate that 54.7% of bee motion at the hive entrance can be predicted accurately with data records spaced 15 minutes apart, and 88.6% of the bee motion can be predicted accurately for those 15 minute measurements averaged over 12 hours. We suggest that these predictions can be used to trigger remote alerts for bee keepers when the observed behavior significantly differs from the predicted values. We also propose that the nine-hour relative humidity trend is a major predictor variable in addition to solar radiation and temperature. Additionally, we show that nearly 19% of the changes in bee motion at the hive entrance can be explained by the changes in select EMR variables. In conjunction with these findings, we contribute the design and software for our Weather and EMR Sensing Station, along with 12 curated data files to the public for further exploration. We also discuss various correlations, relations, and observations pertaining to variables that may be influencing bee behavior. The associated expenses of this research was approximately 1,500 US dollars.","abstract_has_math":false,"creators":["Hornberger, Daniel G."],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Vladimir A. Kulyukin","Nicholas S. Flann","John Edwards"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:52:42Z","subjects":["Honey bee","weather","electromagnetic radiation","machine learning","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/da79-aba1"],"render_values":[{"text":"https://doi.org/10.26076/da79-aba1","href":"https://doi.org/10.26076/da79-aba1","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8330","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8330","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://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9498","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Vladimir A. Kulyukin","Nicholas S. Flann","John Edwards"]},{"key":"dc:creator","label":"Author","values":["Hornberger, Daniel G."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2021-12-01T08:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["Honey bee","weather","electromagnetic radiation","machine learning","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8330"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/da79-aba1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Honey bees are responsible for pollinating many important crops in the United States. However, honey bee populations have declined significantly since 1961. While some causes of this decline are known, others are not. By utilizing electronic bee hive monitoring (EBM) systems, bee keepers and researchers have an added resource in determining the causes of these declines so that the issues can be remedied. For nearly five months (May through October) during the 2020 honey bee foraging season in Logan, Utah, USA, we collected on-site weather and electromagnetic radiation (EMR) readings and videos of the hive entrances of six bee hives every 15 minutes. Each video was processed to estimate the number of bee motions, and the bee motion counts were paired with the weather and EMR data. We show that an algorithm consisting of many decision trees in concert (called a random forest regressor) can be used to accurately predict bee motion counts from one moment to another. By using specific weather variables coupled with omnidirectional bee motion counts, we demonstrate that 54.7% of bee motion at the hive entrance can be predicted accurately with data records spaced 15 minutes apart, and 88.6% of the bee motion can be predicted accurately for those 15 minute measurements averaged over 12 hours. We suggest that these predictions can be used to trigger remote alerts for bee keepers when the observed behavior significantly differs from the predicted values. We also propose that the nine-hour relative humidity trend is a major predictor variable in addition to solar radiation and temperature. Additionally, we show that nearly 19% of the changes in bee motion at the hive entrance can be explained by the changes in select EMR variables. In conjunction with these findings, we contribute the design and software for our Weather and EMR Sensing Station, along with 12 curated data files to the public for further exploration. We also discuss various correlations, relations, and observations pertaining to variables that may be influencing bee behavior. The associated expenses of this research was approximately 1,500 US dollars."]},{"key":"dc:title","label":"Title","values":["On Predicting Omnidirectional Honey Bee Traffic Using Weather and Electromagnetic Radiation"]}]}],"canonical_facts":{"dc:contributor":["Vladimir A. Kulyukin","Nicholas S. Flann","John Edwards"],"dc:creator":["Hornberger, Daniel G."],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2021-12-01T08:00:00Z"],"dc:description.abstract":["Honey bees are responsible for pollinating many important crops in the United States. However, honey bee populations have declined significantly since 1961. While some causes of this decline are known, others are not. By utilizing electronic bee hive monitoring (EBM) systems, bee keepers and researchers have an added resource in determining the causes of these declines so that the issues can be remedied. For nearly five months (May through October) during the 2020 honey bee foraging season in Logan, Utah, USA, we collected on-site weather and electromagnetic radiation (EMR) readings and videos of the hive entrances of six bee hives every 15 minutes. Each video was processed to estimate the number of bee motions, and the bee motion counts were paired with the weather and EMR data. We show that an algorithm consisting of many decision trees in concert (called a random forest regressor) can be used to accurately predict bee motion counts from one moment to another. By using specific weather variables coupled with omnidirectional bee motion counts, we demonstrate that 54.7% of bee motion at the hive entrance can be predicted accurately with data records spaced 15 minutes apart, and 88.6% of the bee motion can be predicted accurately for those 15 minute measurements averaged over 12 hours. We suggest that these predictions can be used to trigger remote alerts for bee keepers when the observed behavior significantly differs from the predicted values. We also propose that the nine-hour relative humidity trend is a major predictor variable in addition to solar radiation and temperature. Additionally, we show that nearly 19% of the changes in bee motion at the hive entrance can be explained by the changes in select EMR variables. In conjunction with these findings, we contribute the design and software for our Weather and EMR Sensing Station, along with 12 curated data files to the public for further exploration. We also discuss various correlations, relations, and observations pertaining to variables that may be influencing bee behavior. The associated expenses of this research was approximately 1,500 US dollars."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8330"],"dc:identifier.doi":["https://doi.org/10.26076/da79-aba1"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["Honey bee","weather","electromagnetic radiation","machine learning","Computer Sciences"],"dc:title":["On Predicting Omnidirectional Honey Bee Traffic Using Weather and Electromagnetic Radiation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:52:42Z"}