Thermals are regions of rising hot air formed on the ground through the warming of the surface by the sun. Thermals are commonly used by birds and glider pilots to extend flight duration, increase cross-country distance, and conserve energy. This kind of powerless flight using natural sources of lift is called soaring. Once a thermal is encountered, the pilot flies in circles to keep within the thermal, so gaining altitude before flying off to the next thermal and towards the destination. A single thermal can net a pilot thousands of feet of elevation gain, however estimating thermal locations is not an easy task. Pilots look for different indicators: color variation on the ground because the difference in the amount of heat absorbed by the ground varies based on the color/composition, birds circling in an area gaining lift, and certain types of cloud formations (cumulus clouds). The above methods are not always reliable enough and pilots study the weather for thermals by estimating solar heating of the ground using cloud cover and time of year and the lapse rate and dew point of the troposphere. In this paper, we present a Machine Learning based solution for assisting in forecasting thermals. We created a custom dataset using flight data recorded and uploaded to public databases by soaring pilots. We determine where and when the pilot encountered thermals to pull weather and satellite images corresponding to the location and time of the flight. Using this dataset we train an algorithm to automatically predict the location of thermals given as input the current weather conditions and terrain information obtained from Google Earth Engine and thermal regions encountered as truth labels. We were able to converge very well on the training and validation set, proving our method with around a 0.98 F1 score. These results indicate success in creating a custom dataset and a powerful neural network with the necessity of bolstering our custom dataset.
","abstract_html":"<p>Thermals are regions of rising hot air formed on the ground through the warming of the surface by the sun. Thermals are commonly used by birds and glider pilots to extend flight duration, increase cross-country distance, and conserve energy. This kind of powerless flight using natural sources of lift is called soaring. Once a thermal is encountered, the pilot flies in circles to keep within the thermal, so gaining altitude before flying off to the next thermal and towards the destination. A single thermal can net a pilot thousands of feet of elevation gain, however estimating thermal locations is not an easy task. Pilots look for different indicators: color variation on the ground because the difference in the amount of heat absorbed by the ground varies based on the color/composition, birds circling in an area gaining lift, and certain types of cloud formations (cumulus clouds). The above methods are not always reliable enough and pilots study the weather for thermals by estimating solar heating of the ground using cloud cover and time of year and the lapse rate and dew point of the troposphere. In this paper, we present a Machine Learning based solution for assisting in forecasting thermals. We created a custom dataset using flight data recorded and uploaded to public databases by soaring pilots. We determine where and when the pilot encountered thermals to pull weather and satellite images corresponding to the location and time of the flight. Using this dataset we train an algorithm to automatically predict the location of thermals given as input the current weather conditions and terrain information obtained from Google Earth Engine and thermal regions encountered as truth labels. We were able to converge very well on the training and validation set, proving our method with around a 0.98 F1 score. These results indicate success in creating a custom dataset and a powerful neural network with the necessity of bolstering our custom dataset.</p>","abstract_has_math":false,"creators":["Tallman, Jake T"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Maria Pantoja","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-06-01T07:00:00Z","date_published":"2021-06-01T07:00:00Z","updated_at":"2026-07-24T01:32:42Z","subjects":["Machine Learning","Free Flight","Image Segmentation","Satellite Imagery","Deep Learning","Gliding","Artificial Intelligence and Robotics","Aviation Safety and Security","Databases and Information Systems","Data Science","Environmental Monitoring","Fluid Dynamics","Geology","Other Aerospace Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2021.64"],"render_values":[{"text":"10.15368/theses.2021.64","href":"https://doi.org/10.15368/theses.2021.64","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2339","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Maria Pantoja","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Tallman, Jake T"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2021-06-09T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Free Flight","Image Segmentation","Satellite Imagery","Deep Learning","Gliding","Artificial Intelligence and Robotics","Aviation Safety and Security","Databases and Information Systems","Data Science","Environmental Monitoring","Fluid Dynamics","Geology","Other Aerospace Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2339","10.15368/theses.2021.64"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Thermals are regions of rising hot air formed on the ground through the warming of the surface by the sun. Thermals are commonly used by birds and glider pilots to extend flight duration, increase cross-country distance, and conserve energy. This kind of powerless flight using natural sources of lift is called soaring. Once a thermal is encountered, the pilot flies in circles to keep within the thermal, so gaining altitude before flying off to the next thermal and towards the destination. A single thermal can net a pilot thousands of feet of elevation gain, however estimating thermal locations is not an easy task. Pilots look for different indicators: color variation on the ground because the difference in the amount of heat absorbed by the ground varies based on the color/composition, birds circling in an area gaining lift, and certain types of cloud formations (cumulus clouds). The above methods are not always reliable enough and pilots study the weather for thermals by estimating solar heating of the ground using cloud cover and time of year and the lapse rate and dew point of the troposphere. In this paper, we present a Machine Learning based solution for assisting in forecasting thermals. We created a custom dataset using flight data recorded and uploaded to public databases by soaring pilots. We determine where and when the pilot encountered thermals to pull weather and satellite images corresponding to the location and time of the flight. Using this dataset we train an algorithm to automatically predict the location of thermals given as input the current weather conditions and terrain information obtained from Google Earth Engine and thermal regions encountered as truth labels. We were able to converge very well on the training and validation set, proving our method with around a 0.98 F1 score. These results indicate success in creating a custom dataset and a powerful neural network with the necessity of bolstering our custom dataset.
"]},{"key":"dc:title","label":"Title","values":["SOARNET, Deep Learning Thermal Detection for Free Flight"]}]}],"canonical_facts":{"dc:contributor":["Maria Pantoja","Computer Science","College of Engineering"],"dc:creator":["Tallman, Jake T"],"dc:date.available":["2021-06-09T07:00:00Z"],"dc:description.abstract":["Thermals are regions of rising hot air formed on the ground through the warming of the surface by the sun. Thermals are commonly used by birds and glider pilots to extend flight duration, increase cross-country distance, and conserve energy. This kind of powerless flight using natural sources of lift is called soaring. Once a thermal is encountered, the pilot flies in circles to keep within the thermal, so gaining altitude before flying off to the next thermal and towards the destination. A single thermal can net a pilot thousands of feet of elevation gain, however estimating thermal locations is not an easy task. Pilots look for different indicators: color variation on the ground because the difference in the amount of heat absorbed by the ground varies based on the color/composition, birds circling in an area gaining lift, and certain types of cloud formations (cumulus clouds). The above methods are not always reliable enough and pilots study the weather for thermals by estimating solar heating of the ground using cloud cover and time of year and the lapse rate and dew point of the troposphere. In this paper, we present a Machine Learning based solution for assisting in forecasting thermals. We created a custom dataset using flight data recorded and uploaded to public databases by soaring pilots. We determine where and when the pilot encountered thermals to pull weather and satellite images corresponding to the location and time of the flight. Using this dataset we train an algorithm to automatically predict the location of thermals given as input the current weather conditions and terrain information obtained from Google Earth Engine and thermal regions encountered as truth labels. We were able to converge very well on the training and validation set, proving our method with around a 0.98 F1 score. These results indicate success in creating a custom dataset and a powerful neural network with the necessity of bolstering our custom dataset.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2339","10.15368/theses.2021.64"],"dc:subject":["Machine Learning","Free Flight","Image Segmentation","Satellite Imagery","Deep Learning","Gliding","Artificial Intelligence and Robotics","Aviation Safety and Security","Databases and Information Systems","Data Science","Environmental Monitoring","Fluid Dynamics","Geology","Other Aerospace Engineering"],"dc:title":["SOARNET, Deep Learning Thermal Detection for Free Flight"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:42Z"}