{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108438"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108438","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning-based crop management optimization using multi-stream convolutional neural networks","abstract":"Improving crop management is an essential step towards solving the food security challenge. Despite the advances in precision agriculture, new methods are needed to create decision-support systems to help farmers increase productivity while accounting for environmental impacts and financial risks. This dissertation presents a class of learning-based optimization algorithms for spatial allocation of crop inputs, and a new framework for online coverage path planning with potential use in tasks such as planting and harvesting. The proposed algorithms use Multi-stream Convolutional Neural Networks (MSCNN) to learn relevant spatial features from the environment and use them to optimize the available control inputs. In the crop inputs optimization problem, an MSCNN combines five input variables as in a regression problem to better predict yield. The predictive model is then used as the base of a gradient-ascent algorithm to maximize a custom objective function. To leverage the applicability of this algorithm, a risk-aware version of this method is also proposed. The predictive uncertainty is measured and used as a constraint to comply with different levels of risk-aversion. Experiments with real crop fields demonstrate that this method significantly reduces the yield prediction errors when compared to the state of the art algorithms. Results from the optimization algorithm show an increase in the expected net revenue of up to 6.8% when compared with the status quo management while providing safety bounds. In the coverage path planning framework, an MSCNN agent learns a control policy from demonstrations of paths obtained offline through heuristic algorithms, by using imitation learning. The resulting control policy is further improved through policy-gradient reinforcement learning. Simulations show that the improved control policy outperforms the offline algorithms used during the imitation learning phase, and that the proposed framework can be easily adapted to different cost functions.","abstract_html":"Improving crop management is an essential step towards solving the food security challenge. Despite the advances in precision agriculture, new methods are needed to create decision-support systems to help farmers increase productivity while accounting for environmental impacts and financial risks. This dissertation presents a class of learning-based optimization algorithms for spatial allocation of crop inputs, and a new framework for online coverage path planning with potential use in tasks such as planting and harvesting. The proposed algorithms use Multi-stream Convolutional Neural Networks (MSCNN) to learn relevant spatial features from the environment and use them to optimize the available control inputs. In the crop inputs optimization problem, an MSCNN combines five input variables as in a regression problem to better predict yield. The predictive model is then used as the base of a gradient-ascent algorithm to maximize a custom objective function. To leverage the applicability of this algorithm, a risk-aware version of this method is also proposed. The predictive uncertainty is measured and used as a constraint to comply with different levels of risk-aversion. Experiments with real crop fields demonstrate that this method significantly reduces the yield prediction errors when compared to the state of the art algorithms. Results from the optimization algorithm show an increase in the expected net revenue of up to 6.8% when compared with the status quo management while providing safety bounds. In the coverage path planning framework, an MSCNN agent learns a control policy from demonstrations of paths obtained offline through heuristic algorithms, by using imitation learning. The resulting control policy is further improved through policy-gradient reinforcement learning. Simulations show that the improved control policy outperforms the offline algorithms used during the imitation learning phase, and that the proposed framework can be easily adapted to different cost functions.","abstract_has_math":false,"creators":["Ormiga Galvao Barbosa, Alexandre"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":["Hovakimyan, Naira","Martin, Nicolas","Salapaka, Srinivasa","Voulgaris, Petros","Shi, Humphrey"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-10-07T20:59:27Z","date_published":"2020-10-07T20:59:27Z","updated_at":"2026-07-22T22:24:48Z","subjects":["Convolutional Neural Networks","Deep Learning","On-farm Research","Yield Modeling","Risk-averse Optimization","Deep Ensemble","Reinforcement Learning","Coverage Path Planning","Imitation Learning"],"languages":["en"],"rights":["Copyright 2020 Alexandre Ormiga Galvao Barbosa"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108438","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hovakimyan, Naira","Martin, Nicolas","Salapaka, Srinivasa","Voulgaris, Petros","Shi, Humphrey"]},{"key":"dc:creator","label":"Author","values":["Ormiga Galvao Barbosa, Alexandre"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-10-07T20:59:27Z","2020-07-06","2020-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["Convolutional Neural Networks","Deep Learning","On-farm Research","Yield Modeling","Risk-averse Optimization","Deep Ensemble","Reinforcement Learning","Coverage Path Planning","Imitation Learning"]}]},{"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 Alexandre Ormiga Galvao Barbosa"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108438"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Improving crop management is an essential step towards solving the food security challenge. Despite the advances in precision agriculture, new methods are needed to create decision-support systems to help farmers increase productivity while accounting for environmental impacts and financial risks. This dissertation presents a class of learning-based optimization algorithms for spatial allocation of crop inputs, and a new framework for online coverage path planning with potential use in tasks such as planting and harvesting. The proposed algorithms use Multi-stream Convolutional Neural Networks (MSCNN) to learn relevant spatial features from the environment and use them to optimize the available control inputs. In the crop inputs optimization problem, an MSCNN combines five input variables as in a regression problem to better predict yield. The predictive model is then used as the base of a gradient-ascent algorithm to maximize a custom objective function. To leverage the applicability of this algorithm, a risk-aware version of this method is also proposed. The predictive uncertainty is measured and used as a constraint to comply with different levels of risk-aversion. Experiments with real crop fields demonstrate that this method significantly reduces the yield prediction errors when compared to the state of the art algorithms. Results from the optimization algorithm show an increase in the expected net revenue of up to 6.8% when compared with the status quo management while providing safety bounds. In the coverage path planning framework, an MSCNN agent learns a control policy from demonstrations of paths obtained offline through heuristic algorithms, by using imitation learning. The resulting control policy is further improved through policy-gradient reinforcement learning. Simulations show that the improved control policy outperforms the offline algorithms used during the imitation learning phase, and that the proposed framework can be easily adapted to different cost functions.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-10-02 without embargo terms","The student, Alexandre Ormiga Galvao Barbosa, accepted the attached license on 2020-06-29 at 20:05.","The student, Alexandre Ormiga Galvao Barbosa, submitted this Dissertation for approval on 2020-06-29 at 20:16.","This Dissertation was approved for publication on 2020-07-06 at 14:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15478 on 2020-10-02 at 15:10:42","Made available in DSpace on 2020-10-07T20:59:27Z (GMT). No. of bitstreams: 2 ORMIGAGALVAOBARBOSA-DISSERTATION-2020.pdf: 6205252 bytes, checksum: 9cc58b71d058a871e80ce285bd3ea2c7 (MD5) LICENSE.txt: 4228 bytes, checksum: d31536bf6d496e6cc72ab9d2ccb700d2 (MD5) Previous issue date: 2020-07-06"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Learning-based crop management optimization using multi-stream convolutional neural networks"]}]}],"canonical_facts":{"dc:contributor":["Hovakimyan, Naira","Martin, Nicolas","Salapaka, Srinivasa","Voulgaris, Petros","Shi, Humphrey"],"dc:creator":["Ormiga Galvao Barbosa, Alexandre"],"dc:date":["2020-10-07T20:59:27Z","2020-07-06","2020-08"],"dc:description":["Improving crop management is an essential step towards solving the food security challenge. Despite the advances in precision agriculture, new methods are needed to create decision-support systems to help farmers increase productivity while accounting for environmental impacts and financial risks. This dissertation presents a class of learning-based optimization algorithms for spatial allocation of crop inputs, and a new framework for online coverage path planning with potential use in tasks such as planting and harvesting. The proposed algorithms use Multi-stream Convolutional Neural Networks (MSCNN) to learn relevant spatial features from the environment and use them to optimize the available control inputs. In the crop inputs optimization problem, an MSCNN combines five input variables as in a regression problem to better predict yield. The predictive model is then used as the base of a gradient-ascent algorithm to maximize a custom objective function. To leverage the applicability of this algorithm, a risk-aware version of this method is also proposed. The predictive uncertainty is measured and used as a constraint to comply with different levels of risk-aversion. Experiments with real crop fields demonstrate that this method significantly reduces the yield prediction errors when compared to the state of the art algorithms. Results from the optimization algorithm show an increase in the expected net revenue of up to 6.8% when compared with the status quo management while providing safety bounds. In the coverage path planning framework, an MSCNN agent learns a control policy from demonstrations of paths obtained offline through heuristic algorithms, by using imitation learning. The resulting control policy is further improved through policy-gradient reinforcement learning. Simulations show that the improved control policy outperforms the offline algorithms used during the imitation learning phase, and that the proposed framework can be easily adapted to different cost functions.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-10-02 without embargo terms","The student, Alexandre Ormiga Galvao Barbosa, accepted the attached license on 2020-06-29 at 20:05.","The student, Alexandre Ormiga Galvao Barbosa, submitted this Dissertation for approval on 2020-06-29 at 20:16.","This Dissertation was approved for publication on 2020-07-06 at 14:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15478 on 2020-10-02 at 15:10:42","Made available in DSpace on 2020-10-07T20:59:27Z (GMT). No. of bitstreams: 2 ORMIGAGALVAOBARBOSA-DISSERTATION-2020.pdf: 6205252 bytes, checksum: 9cc58b71d058a871e80ce285bd3ea2c7 (MD5) LICENSE.txt: 4228 bytes, checksum: d31536bf6d496e6cc72ab9d2ccb700d2 (MD5) Previous issue date: 2020-07-06"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108438"],"dc:language":["en"],"dc:rights":["Copyright 2020 Alexandre Ormiga Galvao Barbosa"],"dc:subject":["Convolutional Neural Networks","Deep Learning","On-farm Research","Yield Modeling","Risk-averse Optimization","Deep Ensemble","Reinforcement Learning","Coverage Path Planning","Imitation Learning"],"dc:title":["Learning-based crop management optimization using multi-stream convolutional neural networks"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:48Z"}