{"id":"W4200114671","doi":"10.5194/amt-14-7511-2021","title":"Assessing the feasibility of using a neural network to filter Orbiting Carbon Observatory 2 (OCO-2) retrievals at northern high latitudes","year":2021,"lang":"en","type":"article","venue":"Atmospheric measurement techniques","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Goddard Space Flight Center; Canadian Space Agency; Jet Propulsion Laboratory; Environment and Climate Change Canada; Deutsches Zentrum für Luft- und Raumfahrt; California Institute of Technology; European Space Agency; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Environmental science; Filter (signal processing); Latitude; Throughput; Observatory; Arctic; Remote sensing; Meteorology; Atmospheric sciences; Computer science; Geology; Geodesy; Oceanography; Telecommunications; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001373589,0.0005594112,0.0002288876,0.0004360332,0.0004132068,0.0004964941,0.0003742533,0.0006749909,0.0007271448],"category_scores_gemma":[0.0040828,0.0002217462,0.0003003207,0.0003257916,0.0001864509,0.0007625878,0.0002752812,0.0003286842,0.0001809109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006790328,"about_ca_system_score_gemma":0.0006392499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03783261,"about_ca_topic_score_gemma":0.0426568,"domain_scores_codex":[0.9997543,0.00005150963,0.00001649088,0.00007296932,0.00006290535,0.00004191239],"domain_scores_gemma":[0.9984584,0.0008506171,0.0001347797,0.00008875145,0.0004231237,0.00004440148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002034095,0.0007862424,0.2839743,0.0001812622,0.0006661905,0.0001783627,0.0001208077,0.4326029,0.0698659,0.0006230152,0.001787274,0.2071796],"study_design_scores_gemma":[0.00003763378,0.0002223291,0.0458382,0.000009139655,0.00007256329,0.00001876688,0.00003520056,0.9370369,0.01621208,0.000181561,0.0003189057,0.00001681402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651288,0.0001528441,0.03186169,0.0001783104,0.0000434018,0.0000437644,0.0002792213,0.0003925937,0.001919437],"genre_scores_gemma":[0.9775062,0.00004160962,0.02131247,0.00005706866,0.00001279541,0.00001959043,0.0003512937,0.00002104625,0.000677863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03783261,"threshold_uncertainty_score":0.07522482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06739862303166802,"score_gpt":0.2819908825099631,"score_spread":0.2145922594782951,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}