{"id":"W4207067814","doi":"10.1109/ssci50451.2021.9660188","title":"A Machine Learning - Explainable AI approach to tropospheric dynamics analysis using Water Vapor Meteosat images","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"European Organization for the Exploitation of Meteorological Satellites","keywords":"Water vapor; Troposphere; Atmosphere (unit); Computer science; Meteorology; Artificial intelligence; Machine learning; Environmental science; 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":[0.0004706687,0.0003407527,0.0003207151,0.0009199156,0.0002416513,0.0006439952,0.0005821549,0.0004121892,0.0009141441],"category_scores_gemma":[0.002588137,0.0001872435,0.0006290418,0.0005594227,0.0004039796,0.0006312711,0.0004337644,0.0008145052,0.00005766183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983752,"about_ca_system_score_gemma":0.0005690424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006642915,"about_ca_topic_score_gemma":0.005183575,"domain_scores_codex":[0.9998426,0.0000709899,0.000007278369,0.00003358719,0.00003029035,0.00001521503],"domain_scores_gemma":[0.9988931,0.0008206292,0.0001189934,0.00006852836,0.00007336701,0.00002552684],"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":[0.00004512477,0.00005845612,0.003835746,0.00006468763,0.0001492708,0.0001061062,0.0001101773,0.899812,0.001664856,0.03824458,0.0006393907,0.05526963],"study_design_scores_gemma":[0.000002655075,0.000006791749,0.000416832,0.000001696088,0.000004270369,0.000004490751,0.0000049911,0.990918,0.0001074144,0.008391572,0.000138986,0.00000246167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09651402,0.0004300603,0.899682,0.0006156062,0.00003126472,0.00005014044,0.0002997541,0.0002764742,0.002100709],"genre_scores_gemma":[0.8564836,0.000243818,0.141293,0.00007188143,0.00008812331,0.00008192428,0.000367394,0.00003325056,0.001336907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006642915,"threshold_uncertainty_score":0.01320851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02454978364612597,"score_gpt":0.2534632216031026,"score_spread":0.2289134379569766,"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."}}