{"id":2652,"date":"2021-07-09T19:50:10","date_gmt":"2021-07-09T10:50:10","guid":{"rendered":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/?page_id=2652"},"modified":"2023-11-14T13:43:03","modified_gmt":"2023-11-14T04:43:03","slug":"machine-learning-approach","status":"publish","type":"page","link":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/en\/research\/machine-learning-approach.html","title":{"rendered":"Machine learning approach"},"content":{"rendered":"<p><span style=\"color: #a02438;\"><strong>Atmospheric density estimation using machine learning approach<\/strong><\/span><br \/>\nVery-low-Earth orbit (VLEO), which is at the 400&#8211;100 km altitude, is an area where many satellites will remain in the future. However, their atmospheric characteristics are still unclear. Because atmospheric density has a critical impact on space missions using satellites, it is necessary to establish a method to estimate it. Our laboratory is reconstructing a methodology to estimate atmospheric density in VLEO using GPS positioning data from the nanosatellite, &#8220;EGG,&#8221; which was demonstrated in 2017. Machine learning approaches, which are Gaussian-process regression and Bayesian optimization, have been adopted to clarify the atmospheric density in VLEO using data acquired by nanosatellites.<\/p>\n<figure id=\"attachment_3047\" aria-describedby=\"caption-attachment-3047\" style=\"width: 300px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" class=\"wp-image-3047 size-medium\" src=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/EGG_mission-300x190.png\" alt=\"\" width=\"300\" height=\"190\" srcset=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/EGG_mission-300x190.png 300w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/EGG_mission-644x407.png 644w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/EGG_mission.png 734w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><figcaption id=\"caption-attachment-3047\" class=\"wp-caption-text\">Mission sequence of nanosatellite, EGG<\/figcaption><\/figure>\n<figure id=\"attachment_3046\" aria-describedby=\"caption-attachment-3046\" style=\"width: 300px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" class=\"wp-image-3046 size-medium\" src=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit-300x178.png\" alt=\"\" width=\"300\" height=\"178\" srcset=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit-300x178.png 300w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit-644x381.png 644w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit-768x455.png 768w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit-1536x909.png 1536w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Earth_orbit.png 1644w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><figcaption id=\"caption-attachment-3046\" class=\"wp-caption-text\">Trajectory analysis result<\/figcaption><\/figure>\n<figure id=\"attachment_3048\" aria-describedby=\"caption-attachment-3048\" style=\"width: 300px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" class=\"wp-image-3048 size-medium\" src=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Reconstruct_orbit-300x206.png\" alt=\"\" width=\"300\" height=\"206\" srcset=\"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Reconstruct_orbit-300x206.png 300w, https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-content\/uploads\/2023\/02\/Reconstruct_orbit.png 633w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><figcaption id=\"caption-attachment-3048\" class=\"wp-caption-text\">Trajectory reconstruction using machine learning approach<\/figcaption><\/figure>\n<p><span style=\"color: #a0283a;\"><strong><span style=\"font-size: 18pt;\"><span style=\"font-size: 14pt;\">Related paper<\/span><\/span><\/strong><\/span><\/p>\n<ul style=\"list-style-type: disc;\">\n<li>Y. Takahashi, M. Saito, N. Oshima, and K. Yamada, &#8220;Trajectory reconstruction for nanosatellite in very low Earth orbit using machine learning,&#8221; Acta Astronautica, vol. 194, pp. 301-308, 2022, DOI : 10.1016\/j.actaastro.2022.02.010<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Atmospheric density estimation using machine learning approach Very-low-Earth orbit (VLEO), which is at the 40&#8230;<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":2646,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_locale":"en_US","_original_post":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/?page_id=2584"},"_links":{"self":[{"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/pages\/2652"}],"collection":[{"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/comments?post=2652"}],"version-history":[{"count":6,"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/pages\/2652\/revisions"}],"predecessor-version":[{"id":3168,"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/pages\/2652\/revisions\/3168"}],"up":[{"embeddable":true,"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/pages\/2646"}],"wp:attachment":[{"href":"https:\/\/c-mng.cwh.hokudai.ac.jp\/stl.eng\/Root\/wp-json\/wp\/v2\/media?parent=2652"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}