{"id":"W4383040563","doi":"10.1017/eds.2023.15","title":"Neural style transfer between observed and simulated cloud images to improve the detection performance of tropical cyclone precursors","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Tropical and Extratropical Cyclones Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Precursory Research for Embryonic Science and Technology; Core Research for Evolutional Science and Technology; Japan Society for the Promotion of Science","keywords":"Tropical cyclone; Cloud computing; Observational study; Computer science; Cyclone (programming language); Artificial intelligence; Artificial neural network; Transfer of learning; Remote sensing; Meteorology; Environmental science; Machine learning; Geography; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002632565,0.0001099416,0.0001325212,0.00006039394,0.0003480951,0.00006748374,0.0008764181,0.0000364005,0.000140401],"category_scores_gemma":[0.00005771143,0.00006922851,0.00002153209,0.0005461219,0.0009349051,0.0006425417,0.0002219982,0.0001857918,0.0001189919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000734397,"about_ca_system_score_gemma":0.00001253824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007971069,"about_ca_topic_score_gemma":0.0002444929,"domain_scores_codex":[0.9982805,0.00006413857,0.000195928,0.0004751314,0.0005760203,0.0004083355],"domain_scores_gemma":[0.9991637,0.0001612826,0.00001886728,0.0004335272,0.000004801178,0.0002177722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006558714,0.00001100913,0.8692822,0.00001040607,0.000004334114,0.000001875633,0.00007341075,0.0007483239,0.03505813,0.000001378298,0.000008517445,0.09473478],"study_design_scores_gemma":[0.0001598667,0.0003941651,0.9489836,0.00000366284,0.000007342906,0.000001720813,0.00007169974,0.0426323,0.007343991,0.000009043085,0.0003028689,0.00008973568],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983636,0.00006278254,0.00009919738,0.0003384068,0.000114638,0.0002531337,0.0007235614,0.00002601339,0.0000186548],"genre_scores_gemma":[0.9995669,0.0001112383,0.00006320556,0.00003385221,0.00007911329,0.000001138084,0.0001140012,0.000003009289,0.00002760345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09464505,"threshold_uncertainty_score":0.3444697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03664549960562104,"score_gpt":0.2454391275137511,"score_spread":0.2087936279081301,"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."}}