{"id":"W4391509534","doi":"10.1029/2023sw003652","title":"Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning","year":2024,"lang":"en","type":"article","venue":"Space Weather","topic":"Ionosphere and magnetosphere dynamics","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trillium Therapeutics (Canada)","funders":"Natural Environment Research Council; Sight Research UK; National Aeronautics and Space Administration","keywords":"Low earth orbit; Orbit (dynamics); Earth (classical element); Astrobiology; Computer science; Physics; Aerospace engineering; Astronomy; Engineering; Satellite","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008732265,0.0001759191,0.0001469589,0.00001755315,0.00008998281,0.00009475682,0.00007967625,0.00004303883,0.001917332],"category_scores_gemma":[0.000002349672,0.0001393053,0.00006232873,0.0002963413,0.00003577166,0.0001548679,0.00004135926,0.0003916046,0.0001353584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002755103,"about_ca_system_score_gemma":0.00008406363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002693729,"about_ca_topic_score_gemma":0.0009728562,"domain_scores_codex":[0.9991759,0.00003398539,0.0001162717,0.0002838652,0.0001108979,0.000279049],"domain_scores_gemma":[0.9996878,0.00003182625,0.00003442652,0.0001676566,0.00002351373,0.00005478891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002002247,0.000610356,0.6573113,0.0002811762,0.0005535443,0.0001878124,0.005539909,0.04726715,0.008409536,0.07869063,0.0008845142,0.2000639],"study_design_scores_gemma":[0.00159564,0.0005415222,0.02465509,0.0004908884,0.0001629131,0.00001880159,0.002994784,0.921495,0.0009874442,0.002197446,0.04371982,0.001140655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8507521,0.0005596192,0.08948951,0.0002556665,0.0002702362,0.0003184031,0.00001451762,0.0002706664,0.05806934],"genre_scores_gemma":[0.9713235,0.00000540533,0.001342832,0.00001830257,0.0001856774,0.0000220817,0.00001804811,0.00005145922,0.02703265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8742278,"threshold_uncertainty_score":0.9989951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0025213318582058,"score_gpt":0.1822500308412953,"score_spread":0.1797286989830895,"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."}}