[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”4.16″ background_image=”https:\/\/oceanopticsconference.org\/wp-content\/uploads\/2022\/01\/oo22-banner-bckd.jpg” background_position=”bottom_left” custom_padding=”54px||54px||true|” locked=”off” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row admin_label=”row” _builder_version=”4.16″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_padding=”||22px|||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||” theme_builder_area=”post_content”][et_pb_text admin_label=”header” _builder_version=”4.18.0″ header_font=”|||on|||||” header_text_color=”#FFFFFF” header_font_size=”42px” global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n
[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”4.18.0″ custom_padding=”||44px|||” border_width_top=”2px” border_color_top=”#e8e8e8″ border_width_bottom=”2px” border_color_bottom=”#e8e8e8″ locked=”off” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row _builder_version=”4.17.4″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_padding=”2px|||||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||” theme_builder_area=”post_content”][et_pb_text admin_label=”Extended abstracts” _builder_version=”4.18.0″ text_font=”|||on|||||” link_font=”||||on||||” header_3_font=”|800|||||||” header_3_text_color=”#057184″ header_3_font_size=”20px” header_3_line_height=”1.3em” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”7px||2px|||” custom_padding=”||31px|||” use_border_color=”off” locked=”off” global_colors_info=”{}” link_text_color__hover=”#a5a5a5″ link_text_color__hover_enabled=”on|hover” theme_builder_area=”post_content”]<\/p>\n
Poster Session 2<\/a>, Tuesday,\u00a0 October\u00a0 4, 10:40\u201312:40<\/p>\n [\/et_pb_text][et_pb_text admin_label=”Extended abstracts” _builder_version=”4.18.0″ link_font=”||||on||||” header_3_font=”|800||on|||||” header_3_text_color=”#057184″ header_3_font_size=”20px” header_3_line_height=”1.2em” header_5_font=”|||on|||||” header_5_text_color=”#545454″ header_5_font_size=”17px” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”7px||15px|||” hover_enabled=”0″ use_border_color=”off” global_colors_info=”{}” link_text_color__hover=”#a5a5a5″ link_text_color__hover_enabled=”on|hover” theme_builder_area=”post_content” sticky_enabled=”0″]<\/p>\n [\/et_pb_text][et_pb_text admin_label=”Extended abstracts” _builder_version=”4.18.0″ link_font=”||||on||||” header_3_font=”|800||on|||||” header_3_text_color=”#057184″ header_3_font_size=”20px” header_3_line_height=”1.2em” header_5_font=”|||on|||||” header_5_font_size=”17px” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”7px|||||” hover_enabled=”0″ use_border_color=”off” global_colors_info=”{}” link_text_color__hover=”#a5a5a5″ link_text_color__hover_enabled=”on|hover” theme_builder_area=”post_content” sticky_enabled=”0″]<\/p>\n The primary challenge for the remote sensing of aquatic ecosystems via modern remote sensing systems revolves around formulating and implementing a robust atmospheric correction (AC) model to predict remote sensing reflectance (R rs ). This presentation describes the concept of a machine-learning model implemented for estimating R rs from Landsat-8\u2019s Operational Land Imager\u2019s (OLI) observations over inland and coastal waters. First, a well-validated, coupled ocean-atmosphere radiative transfer (RT) model was adapted to integrate into situ R rs as the surface boundary condition. OLI\u2019s top-of-atmosphere reflectance spectra (rhot) were simulated for a plausible range of imaging geometries and aerosol contents, as well as for a broad range of in situ R rs spectra. Second, a class of neural networks, i.e., mixture density networks that model the conditional probability of input-output variables, was designed and tested to transform OLI\u2019s simulated rhot to R rs . The model was then applied to OLI imagery for an extensive matchup assessment. Compared to other existing AC processors, our matchup assessments (N > 500) showed performance improvements from 20 to more than 100%, depending on the spectral band, statistical metrics, and benchmark AC processors. Median uncertainties for the performance of our model were 16%, 15%, 19%, and 30% for OLI\u2019s 443, 482, 560, and 655 nm spectral bands, respectively. Our model notably exhibited superior performance in reducing retrieval noise, as evidenced by the root-mean-square statistics relative to benchmark processors. These preliminary results suggest that our methodology is a promising approach to the inverse problem of AC.<\/p>\n Nima Pahlevan<\/strong><\/a>, SSAI \/ NASA GSFC, nima.pahlevan@nasa.gov<\/p>\n Akash Ashapure, SSAI, akash.ashapure@ssaihq.com\u00a0<\/p>\n Brandon Smith, SSAI, brandon.smith@ssaihq.com\u00a0<\/p>\n Pengwang Zhai, University of Maryland Baltimore County, pwzhai@umbc.edu<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ custom_padding_last_edited=”on|tablet” _builder_version=”4.14.7″ _module_preset=”default” background_enable_color=”off” background_image=”https:\/\/oceanopticsconference.org\/wp-content\/uploads\/2022\/01\/oo22-banner-bckd.jpg” custom_padding=”0px||11px||false|false” custom_padding_tablet=”0px||11px||false|false” custom_padding_phone=”||27px||false|false” global_module=”2766″ saved_tabs=”all” locked=”off” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row _builder_version=”4.16″ _module_preset=”default” custom_padding=”0px||8px||false|false” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”4_4″ _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_social_media_follow use_icon_font_size=”on” icon_font_size=”19px” _builder_version=”4.16″ _module_preset=”default” custom_button=”on” text_orientation=”right” custom_margin=”-10px||11px||false|false” custom_margin_tablet=”-9px||5px||false|false” custom_margin_phone=”-9px||5px||false|false” custom_margin_last_edited=”on|tablet” global_colors_info=”{}” button_text_size__hover_enabled=”on|desktop” theme_builder_area=”post_content”][et_pb_social_media_follow_network social_network=”facebook” url=”https:\/\/www.facebook.com\/OceanOpticsConference\/” _builder_version=”4.16″ _module_preset=”default” background_color=”#9b9b9b” background_enable_color=”on” global_colors_info=”{}” background__hover_enabled=”on|hover” background_color__hover=”#0C71C3″ background_enable_color__hover=”on” theme_builder_area=”post_content” follow_button=”off” url_new_window=”on”]facebook[\/et_pb_social_media_follow_network][et_pb_social_media_follow_network social_network=”twitter” url=”https:\/\/twitter.com\/OceanOpticsConf” _builder_version=”4.16″ _module_preset=”default” background_color=”#9b9b9b” background_enable_color=”on” global_colors_info=”{}” background__hover_enabled=”on|hover” background_color__hover=”#0C71C3″ background_enable_color__hover=”on” theme_builder_area=”post_content” follow_button=”off” url_new_window=”on”]twitter[\/et_pb_social_media_follow_network][\/et_pb_social_media_follow][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ use_custom_gutter=”on” gutter_width=”2″ _builder_version=”4.16″ _module_preset=”default” custom_padding=”13px||34px|0px||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”1_3″ _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.16″ _module_preset=”default” header_font_size=”26px” header_2_font=”|||on|||||” header_2_text_align=”center” header_2_text_color=”#FFFFFF” header_2_font_size=”21px” text_orientation=”center” custom_margin=”||5px|||” global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n [\/et_pb_text][et_pb_text _builder_version=”4.16″ _module_preset=”default” text_text_color=”#FFFFFF” link_font=”||||on||||” link_text_color=”#FFFFFF” header_2_text_color=”#FFFFFF” max_width=”300px” module_alignment=”center” custom_margin=”||||false|false” custom_margin_tablet=”||-3px||false|false” custom_margin_phone=”” custom_margin_last_edited=”on|tablet” custom_padding_tablet=”||||false|false” custom_padding_phone=”||32px||false|false” custom_padding_last_edited=”on|phone” global_colors_info=”{}” link_text_color__hover_enabled=”on|hover” link_text_color__hover=”#a8a8a8″ theme_builder_area=”post_content”]<\/p>\n Sign up to receive email updates to be sure to catch all the meeting news. [\/et_pb_text][et_pb_button button_url=”https:\/\/tosmc.memberclicks.net\/index.php?option=com_mcform&view=ngforms&id=13832#\/” url_new_window=”on” button_text=”Sign Up” button_alignment=”center” _builder_version=”4.16″ _module_preset=”default” custom_button=”on” button_text_size=”15px” button_bg_color=”#0b83bf” button_border_width=”1px” button_border_radius=”27px” button_use_icon=”off” background_layout=”dark” custom_margin=”21px||||false|false” custom_margin_tablet=”” custom_margin_phone=”-8px||||false|false” custom_margin_last_edited=”on|tablet” global_colors_info=”{}” button_bg_color__hover_enabled=”on|hover” button_bg_color__hover=”#a3a3a3″ button_bg_enable_color__hover=”on” theme_builder_area=”post_content”][\/et_pb_button][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.16″ _module_preset=”default” header_font_size=”26px” header_2_font=”|||on|||||” header_2_text_align=”center” header_2_text_color=”#FFFFFF” header_2_font_size=”21px” text_orientation=”center” custom_margin=”||5px|||” custom_margin_tablet=”20px||5px||false|false” custom_margin_phone=”” custom_margin_last_edited=”on|desktop” global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n [\/et_pb_text][et_pb_text _builder_version=”4.16″ _module_preset=”default” text_text_color=”#FFFFFF” link_font=”||||on||||” link_text_color=”#FFFFFF” header_2_text_color=”#FFFFFF” custom_margin=”||||false|false” custom_padding_tablet=”” custom_padding_phone=”||32px||false|false” custom_padding_last_edited=”on|phone” global_colors_info=”{}” link_text_color__hover_enabled=”on|hover” link_text_color__hover=”#a8a8a8″ theme_builder_area=”post_content”]<\/p>\n Contact Jenny Ramarui, [\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.16″ _module_preset=”default” header_font_size=”26px” header_2_font=”|||on|||||” header_2_text_align=”center” header_2_text_color=”#FFFFFF” header_2_font_size=”21px” text_orientation=”center” custom_margin=”||5px|||” custom_margin_tablet=”12px||5px||false|false” custom_margin_phone=”-12px||5px||false|false” custom_margin_last_edited=”on|tablet” global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n [\/et_pb_text][et_pb_text _builder_version=”4.16″ _module_preset=”default” text_text_color=”#FFFFFF” link_font=”||||on||||” link_text_color=”#FFFFFF” header_2_text_color=”#FFFFFF” global_colors_info=”{}” link_text_color__hover_enabled=”on|hover” link_text_color__hover=”#a8a8a8″ theme_builder_area=”post_content”]<\/p>\n Privacy Policy<\/a> [\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":" PostersPoster Session 2, Tuesday,\u00a0 October\u00a0 4, 10:40\u201312:40Poster 74 Leveraging mixture density networks to compensate for atmospheric effects over inland and coastal watersThe primary challenge for the remote sensing of aquatic ecosystems via modern remote sensing systems revolves around formulating and implementing a robust atmospheric correction (AC) model to predict remote sensing reflectance (R rs ). […]<\/p>\n","protected":false},"author":3,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":""},"_links":{"self":[{"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/pages\/6727"}],"collection":[{"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/comments?post=6727"}],"version-history":[{"count":2,"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/pages\/6727\/revisions"}],"predecessor-version":[{"id":6737,"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/pages\/6727\/revisions\/6737"}],"wp:attachment":[{"href":"https:\/\/oceanopticsconference.org\/wp-json\/wp\/v2\/media?parent=6727"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Poster 74<\/h5>\n
Leveraging mixture density networks to compensate for atmospheric effects over inland and coastal waters<\/h3>\n
Keep up to date<\/h2>\n
<\/a><\/p>\nQuestions?<\/h2>\n
Conference Coordinator,
at info@tos.org<\/a>
or (1) 301-251-7708
<\/a><\/p>\nResources<\/h2>\n
Code of Conduct<\/a><\/p>\n