{"id":"W4413743681","doi":"10.1029/2024gl110661","title":"Tropical Cyclone Multi‐Level Wind‐Speed Structure Reconstruction From Sparse Dropsonde Data Via Adversarial Learning","year":2025,"lang":"en","type":"article","venue":"Geophysical Research Letters","topic":"Tropical and Extratropical Cyclones Research","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"National Key Research and Development Program of China; Shanghai Jiao Tong University; National Natural Science Foundation of China","keywords":"Tropical cyclone; Dropsonde; Meteorology; Cyclone (programming language); Environmental science; Wind speed; Remote sensing; Computer science; Geology; Climatology; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000654049,0.0005070487,0.0003602222,0.0002593298,0.0001621508,0.0003702653,0.0005347895,0.000464096,0.0006123054],"category_scores_gemma":[0.00232452,0.0002979147,0.0003430299,0.0002035426,0.0005665476,0.0004738697,0.0006942979,0.0009794394,0.000107162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004454706,"about_ca_system_score_gemma":0.0004853947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006335313,"about_ca_topic_score_gemma":0.005858469,"domain_scores_codex":[0.9998587,0.00004706249,0.000006015599,0.00003342017,0.00002990393,0.00002483356],"domain_scores_gemma":[0.9990072,0.0006677899,0.0001102122,0.00008332604,0.00008008665,0.00005155755],"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":[0.00002363388,0.00001011493,0.0009941822,0.000006525216,0.000008359355,0.00001824217,0.000007677534,0.9925199,0.0005347684,0.0008351273,0.0002039202,0.004837574],"study_design_scores_gemma":[9.522884e-7,0.000002521438,0.00007104464,5.531642e-7,4.606714e-7,0.000001155581,8.679454e-7,0.9995339,0.0001061429,0.0002642419,0.00001743692,5.880339e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3506671,0.000157571,0.6454373,0.000559598,0.00004872773,0.00004182967,0.0002839635,0.0005410542,0.002262704],"genre_scores_gemma":[0.9804754,0.00004200358,0.01834241,0.00006501518,0.00002013531,0.00001837167,0.0002422294,0.00001944514,0.0007750219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006335313,"threshold_uncertainty_score":0.01259691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07080107629921885,"score_gpt":0.315471643823963,"score_spread":0.2446705675247441,"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."}}