{"id":"W4415112932","doi":"10.5194/amt-19-3539-2026","title":"Extraction of spatially confined small-scale waves from high-resolution all-sky airglow images based on machine learning","year":2025,"lang":"en","type":"article","venue":"Atmospheric measurement techniques","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Infineon Technologies (Canada)","funders":"Bayerisches Staatsministerium für Umwelt und Verbraucherschutz; Deutsches Zentrum für Luft- und Raumfahrt","keywords":"Airglow; Wavelength; Temporal resolution; Image resolution; Instability; Stability (learning theory); Position (finance)","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":[0.0007743395,0.0002129664,0.0003078458,0.00002273485,0.0001729329,0.00003987569,0.0002033751,0.0001276464,0.001888413],"category_scores_gemma":[0.0002305725,0.000172856,0.00009422113,0.000263043,0.00007853138,0.00009651593,0.00001205418,0.0002300283,0.00001520494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003164719,"about_ca_system_score_gemma":0.00006528407,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008490026,"about_ca_topic_score_gemma":0.001354738,"domain_scores_codex":[0.9981511,0.0003104549,0.0004380448,0.0003590542,0.0004982133,0.0002431202],"domain_scores_gemma":[0.9989958,0.0002849782,0.0002148612,0.0002654121,0.000166967,0.00007202099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001043709,0.0004965317,0.3788442,0.0001037241,0.0002169598,0.00001000234,0.0001014183,0.2169484,0.09451893,0.0003620395,0.0008526233,0.3065014],"study_design_scores_gemma":[0.0007356516,0.00107476,0.5655255,0.0001568694,0.000133278,2.988156e-7,0.00002398421,0.3817532,0.03984768,0.003390247,0.006995757,0.0003627253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5166274,0.00109851,0.4424815,0.001352891,0.0004543252,0.001257669,0.0001020102,0.0008920761,0.03573367],"genre_scores_gemma":[0.9282879,0.00005487534,0.07084886,0.0003825455,0.00004198143,0.00001142455,0.000195512,0.000005339017,0.0001715359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4116606,"threshold_uncertainty_score":0.999024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02610591752295057,"score_gpt":0.2324919259940399,"score_spread":0.2063860084710893,"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."}}