{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108732"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108732","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"BlueBird: national-scale real-time crop cover classification using multi-stage deep learning approach","abstract":"An effective real-time crop cover classification prediction is essential to real-time large-scale crop monitoring. High resolution satellite optical data containing distinguishable signals of different crop types have been used by recent crop cover classification studies. However, existing works that merely use satellite information fail to reach a high accuracy, especially in the early growing season (before July) because of lacking informative satellite scenes that can be used to effectively distinguish crops. In this work, we present a deep-learning- based method, named BlueBird, to accurately classify crop cover types in real-time at the national scale. BlueBird consists of three sub-models: prior-knowledge model, real-time optical model, and real-time weight model. Historical planting information, sequence of planted crop types in past years, is incorporated into the prior-knowledge model to improve the performance, especially in the pre and early season when satellite images do not contain distinguishable crop signals. Available satellite optical data is used by the real-time optical model to extract spatial and temporal information that can be used to classify the crops. Finally, BlueBird integrates historical crop planting information with spatial and temporal patterns discovered from satellite time series using a trainable real-time weight model that evolves over time, thereby allowing the satellite-based model to be increasingly dominant as more observation data are available. We also propose a national acreage model based on BlueBird’s real-time prediction to predict the national acreage of two major crops, corn and soybean. We conduct leave-one-year-out validations in the whole U.S. Corn Belt from 2014 to 2019 to evaluate the real-time performance of BlueBird. We generate F1 score maps thatcompare BlueBird’s predictions with CDL and scatter plots that compare BlueBird’s county- level acreage with NASS’s ground truth to demonstrate the large-scale effectiveness. In the map of June 1, we can see that corn belt counties where corn and soybean are dominant crop types generally reach 0.8 F1 score. Same promising results can be concluded from the scatter plot of June 1, that for both corn and soybean, most years reach a r 2 above 0.85. From the accuracy map and scatter plot on August 30 , we can see the significant improvement from initial predictions to end-of-season predictions. In the detailed analysis of Champaign, Illinois, BlueBird achieves F1 scores of 0.88 on June 1 for all the validation years and end-of-season F1 scores above 0.95 for all years except 2019 when historic flooding and precipitation happens. We use BlueBird’s prediction to evaluate our national acreage model using the ground truth released by NASS. Error of Corn acreage has a RMSE of 2.12% on June 1 and a RMSE of 1.36% on August 30. Error of soybean acreage (2014 to2018) has a RMSE of 1.70% on June 1 and a RMSE of 0.85% on August 30. The extensive results demonstrate that BlueBird is capable of generating highly accurate real-time crop cover in national-scale and the national acreage model is effective in predicting corn and soybean acreages.","abstract_html":"An effective real-time crop cover classification prediction is essential to real-time large-scale crop monitoring. High resolution satellite optical data containing distinguishable signals of different crop types have been used by recent crop cover classification studies. However, existing works that merely use satellite information fail to reach a high accuracy, especially in the early growing season (before July) because of lacking informative satellite scenes that can be used to effectively distinguish crops. In this work, we present a deep-learning- based method, named BlueBird, to accurately classify crop cover types in real-time at the national scale. BlueBird consists of three sub-models: prior-knowledge model, real-time optical model, and real-time weight model. Historical planting information, sequence of planted crop types in past years, is incorporated into the prior-knowledge model to improve the performance, especially in the pre and early season when satellite images do not contain distinguishable crop signals. Available satellite optical data is used by the real-time optical model to extract spatial and temporal information that can be used to classify the crops. Finally, BlueBird integrates historical crop planting information with spatial and temporal patterns discovered from satellite time series using a trainable real-time weight model that evolves over time, thereby allowing the satellite-based model to be increasingly dominant as more observation data are available. We also propose a national acreage model based on BlueBird’s real-time prediction to predict the national acreage of two major crops, corn and soybean. We conduct leave-one-year-out validations in the whole U.S. Corn Belt from 2014 to 2019 to evaluate the real-time performance of BlueBird. We generate F1 score maps thatcompare BlueBird’s predictions with CDL and scatter plots that compare BlueBird’s county- level acreage with NASS’s ground truth to demonstrate the large-scale effectiveness. In the map of June 1, we can see that corn belt counties where corn and soybean are dominant crop types generally reach 0.8 F1 score. Same promising results can be concluded from the scatter plot of June 1, that for both corn and soybean, most years reach a r 2 above 0.85. From the accuracy map and scatter plot on August 30 , we can see the significant improvement from initial predictions to end-of-season predictions. In the detailed analysis of Champaign, Illinois, BlueBird achieves F1 scores of 0.88 on June 1 for all the validation years and end-of-season F1 scores above 0.95 for all years except 2019 when historic flooding and precipitation happens. We use BlueBird’s prediction to evaluate our national acreage model using the ground truth released by NASS. Error of Corn acreage has a RMSE of 2.12% on June 1 and a RMSE of 1.36% on August 30. Error of soybean acreage (2014 to2018) has a RMSE of 1.70% on June 1 and a RMSE of 0.85% on August 30. The extensive results demonstrate that BlueBird is capable of generating highly accurate real-time crop cover in national-scale and the national acreage model is effective in predicting corn and soybean acreages.","abstract_has_math":false,"creators":["Huang, Yizhi"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Peng, Jian"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-10-07T22:50:09Z","date_published":"2020-10-07T22:50:09Z","updated_at":"2026-07-22T22:24:48Z","subjects":["Crop Type","Satellite Image","Land Cover","Real Time Crop Type Classification","Real Time Land Cover Classification"],"languages":["en"],"rights":["Copyright 2020 Yizhi Huang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108732","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Peng, Jian"]},{"key":"dc:creator","label":"Author","values":["Huang, Yizhi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-10-07T22:50:09Z","2022-10-07T22:50:13Z","2020-07-23","2020-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Crop Type","Satellite Image","Land Cover","Real Time Crop Type Classification","Real Time Land Cover Classification"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Yizhi Huang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108732"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["An effective real-time crop cover classification prediction is essential to real-time large-scale crop monitoring. High resolution satellite optical data containing distinguishable signals of different crop types have been used by recent crop cover classification studies. However, existing works that merely use satellite information fail to reach a high accuracy, especially in the early growing season (before July) because of lacking informative satellite scenes that can be used to effectively distinguish crops. In this work, we present a deep-learning- based method, named BlueBird, to accurately classify crop cover types in real-time at the national scale. BlueBird consists of three sub-models: prior-knowledge model, real-time optical model, and real-time weight model. Historical planting information, sequence of planted crop types in past years, is incorporated into the prior-knowledge model to improve the performance, especially in the pre and early season when satellite images do not contain distinguishable crop signals. Available satellite optical data is used by the real-time optical model to extract spatial and temporal information that can be used to classify the crops. Finally, BlueBird integrates historical crop planting information with spatial and temporal patterns discovered from satellite time series using a trainable real-time weight model that evolves over time, thereby allowing the satellite-based model to be increasingly dominant as more observation data are available. We also propose a national acreage model based on BlueBird’s real-time prediction to predict the national acreage of two major crops, corn and soybean. We conduct leave-one-year-out validations in the whole U.S. Corn Belt from 2014 to 2019 to evaluate the real-time performance of BlueBird. We generate F1 score maps thatcompare BlueBird’s predictions with CDL and scatter plots that compare BlueBird’s county- level acreage with NASS’s ground truth to demonstrate the large-scale effectiveness. In the map of June 1, we can see that corn belt counties where corn and soybean are dominant crop types generally reach 0.8 F1 score. Same promising results can be concluded from the scatter plot of June 1, that for both corn and soybean, most years reach a r 2 above 0.85. From the accuracy map and scatter plot on August 30 , we can see the significant improvement from initial predictions to end-of-season predictions. In the detailed analysis of Champaign, Illinois, BlueBird achieves F1 scores of 0.88 on June 1 for all the validation years and end-of-season F1 scores above 0.95 for all years except 2019 when historic flooding and precipitation happens. We use BlueBird’s prediction to evaluate our national acreage model using the ground truth released by NASS. Error of Corn acreage has a RMSE of 2.12% on June 1 and a RMSE of 1.36% on August 30. Error of soybean acreage (2014 to2018) has a RMSE of 1.70% on June 1 and a RMSE of 0.85% on August 30. The extensive results demonstrate that BlueBird is capable of generating highly accurate real-time crop cover in national-scale and the national acreage model is effective in predicting corn and soybean acreages.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-08-01","The student, Yizhi Huang, accepted the attached license on 2020-07-22 at 19:47.","The student, Yizhi Huang, submitted this Thesis for approval on 2020-07-22 at 20:02.","This Thesis was approved for publication on 2020-07-23 at 09:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15734 on 2020-10-02 at 15:52:21","Made available in DSpace on 2020-10-07T22:50:09Z (GMT). No. of bitstreams: 3 HUANG-THESIS-2020.pdf: 5506608 bytes, checksum: 34e80d45dcab31901c1c3a663218b1c7 (MD5) Thesis_yizhihuang.zip: 5420608 bytes, checksum: 202ecd243eca61a29574aab2a3615c76 (MD5) LICENSE.txt: 4208 bytes, checksum: b2949a6c4dbbd2bebf75c8d33d105eab (MD5) Previous issue date: 2020-07-23","Embargo set by: Seth Robbins for item 116361 Lift date: 2022-10-07T22:50:13Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["BlueBird: national-scale real-time crop cover classification using multi-stage deep learning approach"]}]}],"canonical_facts":{"dc:contributor":["Peng, Jian"],"dc:creator":["Huang, Yizhi"],"dc:date":["2020-10-07T22:50:09Z","2022-10-07T22:50:13Z","2020-07-23","2020-08"],"dc:description":["An effective real-time crop cover classification prediction is essential to real-time large-scale crop monitoring. High resolution satellite optical data containing distinguishable signals of different crop types have been used by recent crop cover classification studies. However, existing works that merely use satellite information fail to reach a high accuracy, especially in the early growing season (before July) because of lacking informative satellite scenes that can be used to effectively distinguish crops. In this work, we present a deep-learning- based method, named BlueBird, to accurately classify crop cover types in real-time at the national scale. BlueBird consists of three sub-models: prior-knowledge model, real-time optical model, and real-time weight model. Historical planting information, sequence of planted crop types in past years, is incorporated into the prior-knowledge model to improve the performance, especially in the pre and early season when satellite images do not contain distinguishable crop signals. Available satellite optical data is used by the real-time optical model to extract spatial and temporal information that can be used to classify the crops. Finally, BlueBird integrates historical crop planting information with spatial and temporal patterns discovered from satellite time series using a trainable real-time weight model that evolves over time, thereby allowing the satellite-based model to be increasingly dominant as more observation data are available. We also propose a national acreage model based on BlueBird’s real-time prediction to predict the national acreage of two major crops, corn and soybean. We conduct leave-one-year-out validations in the whole U.S. Corn Belt from 2014 to 2019 to evaluate the real-time performance of BlueBird. We generate F1 score maps thatcompare BlueBird’s predictions with CDL and scatter plots that compare BlueBird’s county- level acreage with NASS’s ground truth to demonstrate the large-scale effectiveness. In the map of June 1, we can see that corn belt counties where corn and soybean are dominant crop types generally reach 0.8 F1 score. Same promising results can be concluded from the scatter plot of June 1, that for both corn and soybean, most years reach a r 2 above 0.85. From the accuracy map and scatter plot on August 30 , we can see the significant improvement from initial predictions to end-of-season predictions. In the detailed analysis of Champaign, Illinois, BlueBird achieves F1 scores of 0.88 on June 1 for all the validation years and end-of-season F1 scores above 0.95 for all years except 2019 when historic flooding and precipitation happens. We use BlueBird’s prediction to evaluate our national acreage model using the ground truth released by NASS. Error of Corn acreage has a RMSE of 2.12% on June 1 and a RMSE of 1.36% on August 30. Error of soybean acreage (2014 to2018) has a RMSE of 1.70% on June 1 and a RMSE of 0.85% on August 30. The extensive results demonstrate that BlueBird is capable of generating highly accurate real-time crop cover in national-scale and the national acreage model is effective in predicting corn and soybean acreages.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-08-01","The student, Yizhi Huang, accepted the attached license on 2020-07-22 at 19:47.","The student, Yizhi Huang, submitted this Thesis for approval on 2020-07-22 at 20:02.","This Thesis was approved for publication on 2020-07-23 at 09:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15734 on 2020-10-02 at 15:52:21","Made available in DSpace on 2020-10-07T22:50:09Z (GMT). No. of bitstreams: 3 HUANG-THESIS-2020.pdf: 5506608 bytes, checksum: 34e80d45dcab31901c1c3a663218b1c7 (MD5) Thesis_yizhihuang.zip: 5420608 bytes, checksum: 202ecd243eca61a29574aab2a3615c76 (MD5) LICENSE.txt: 4208 bytes, checksum: b2949a6c4dbbd2bebf75c8d33d105eab (MD5) Previous issue date: 2020-07-23","Embargo set by: Seth Robbins for item 116361 Lift date: 2022-10-07T22:50:13Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108732"],"dc:language":["en"],"dc:rights":["Copyright 2020 Yizhi Huang"],"dc:subject":["Crop Type","Satellite Image","Land Cover","Real Time Crop Type Classification","Real Time Land Cover Classification"],"dc:title":["BlueBird: national-scale real-time crop cover classification using multi-stage deep learning approach"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:48Z"}