{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/61516"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/61516","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Improved uncertainty estimates for geophysical parameter retrieval","abstract":"Algorithms for retrieval of geophysical parameters from radiances measured by instruments onboard satellites play a large role in helping scientists monitor the state of the planet. Current retrieval algorithms based on neural networks are superior in accuracy and speed compared to physics-based algorithms like iterated minimum variance (IMV). However, they do not have any form of error estimation, unlike IMV. This thesis examines the suitability of several different approaches to adding in confidence intervals and other methods of error estimation to the retrieval algorithm, as well as alternative machine learning methods that can both retrieve the parameters desired and assign error bars. Test datasets included both current generation operational instruments like AIRS/AMSU, as well as a hypothetical future hyper- spectral microwave sounder. Mixture density networks (MDN) and Sparse Pseudo Input Gaussian processes (SPGP) were found to be the most accurate at variance prediction. Both of these are novel methods in the field of remote sensing. MDNs also had similar training and testing time to neural networks, while SPGPs often took three times as long to train in typical cases. As a baseline, neural networks trained to estimate variance were also tested, but found to be lacking in accuracy and reliability compared to the other methods.","abstract_html":"Algorithms for retrieval of geophysical parameters from radiances measured by instruments onboard satellites play a large role in helping scientists monitor the state of the planet. Current retrieval algorithms based on neural networks are superior in accuracy and speed compared to physics-based algorithms like iterated minimum variance (IMV). However, they do not have any form of error estimation, unlike IMV. This thesis examines the suitability of several different approaches to adding in confidence intervals and other methods of error estimation to the retrieval algorithm, as well as alternative machine learning methods that can both retrieve the parameters desired and assign error bars. Test datasets included both current generation operational instruments like AIRS/AMSU, as well as a hypothetical future hyper- spectral microwave sounder. Mixture density networks (MDN) and Sparse Pseudo Input Gaussian processes (SPGP) were found to be the most accurate at variance prediction. Both of these are novel methods in the field of remote sensing. MDNs also had similar training and testing time to neural networks, while SPGPs often took three times as long to train in typical cases. As a baseline, neural networks trained to estimate variance were also tested, but found to be lacking in accuracy and reliability compared to the other methods.","abstract_has_math":false,"creators":["Tao, Zuoyu"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["William J. Blackwell and David H. Staelin."],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010","date_published":"2010","updated_at":"2026-07-22T22:21:24Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/61516","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["William J. Blackwell and David H. Staelin."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Tao, Zuoyu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2011-03-07T14:38:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2011-03-07T14:38:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2010"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/61516"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (p. 167-169)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Algorithms for retrieval of geophysical parameters from radiances measured by instruments onboard satellites play a large role in helping scientists monitor the state of the planet. Current retrieval algorithms based on neural networks are superior in accuracy and speed compared to physics-based algorithms like iterated minimum variance (IMV). However, they do not have any form of error estimation, unlike IMV. This thesis examines the suitability of several different approaches to adding in confidence intervals and other methods of error estimation to the retrieval algorithm, as well as alternative machine learning methods that can both retrieve the parameters desired and assign error bars. Test datasets included both current generation operational instruments like AIRS/AMSU, as well as a hypothetical future hyper- spectral microwave sounder. Mixture density networks (MDN) and Sparse Pseudo Input Gaussian processes (SPGP) were found to be the most accurate at variance prediction. Both of these are novel methods in the field of remote sensing. MDNs also had similar training and testing time to neural networks, while SPGPs often took three times as long to train in typical cases. As a baseline, neural networks trained to estimate variance were also tested, but found to be lacking in accuracy and reliability compared to the other methods."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Improved uncertainty estimates for geophysical parameter retrieval"]}]}],"canonical_facts":{"dc:contributor.advisor":["William J. Blackwell and David H. Staelin."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Tao, Zuoyu"],"dc:date.accessioned":["2011-03-07T14:38:17Z"],"dc:date.available":["2011-03-07T14:38:17Z"],"dc:date.issued":["2010"],"dc:description":["Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (p. 167-169)."],"dc:description.abstract":["Algorithms for retrieval of geophysical parameters from radiances measured by instruments onboard satellites play a large role in helping scientists monitor the state of the planet. Current retrieval algorithms based on neural networks are superior in accuracy and speed compared to physics-based algorithms like iterated minimum variance (IMV). However, they do not have any form of error estimation, unlike IMV. This thesis examines the suitability of several different approaches to adding in confidence intervals and other methods of error estimation to the retrieval algorithm, as well as alternative machine learning methods that can both retrieve the parameters desired and assign error bars. Test datasets included both current generation operational instruments like AIRS/AMSU, as well as a hypothetical future hyper- spectral microwave sounder. Mixture density networks (MDN) and Sparse Pseudo Input Gaussian processes (SPGP) were found to be the most accurate at variance prediction. Both of these are novel methods in the field of remote sensing. MDNs also had similar training and testing time to neural networks, while SPGPs often took three times as long to train in typical cases. As a baseline, neural networks trained to estimate variance were also tested, but found to be lacking in accuracy and reliability compared to the other methods."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/61516"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Improved uncertainty estimates for geophysical parameter retrieval"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:24Z"}