{"id":"W2965488766","doi":"10.1175/waf-d-19-0011.1","title":"On the Evaluation of Probabilistic Thunderstorm Forecasts and the Automated Generation of Thunderstorm Threat Areas during Environment Canada Pan Am Science Showcase","year":2019,"lang":"en","type":"article","venue":"Weather and Forecasting","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thunderstorm; Nowcasting; Probabilistic logic; Computer science; Meteorology; Categorical variable; Forecast skill; Consensus forecast; Environmental science; Machine learning; Statistics; Geography; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001381229,0.00009175243,0.0001367393,0.00003284714,0.0003150654,0.00002661457,0.0000928215,0.00002354805,0.0002562385],"category_scores_gemma":[0.0002036123,0.00004581446,0.00002066136,0.0001034491,0.0003574635,0.00009284052,0.00001710282,0.00006097544,9.177259e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002811176,"about_ca_system_score_gemma":0.00009114061,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01703601,"about_ca_topic_score_gemma":0.03393423,"domain_scores_codex":[0.998867,0.0001114788,0.0002077352,0.0001886236,0.0004731582,0.0001519889],"domain_scores_gemma":[0.9990814,0.0005412856,0.000136461,0.0001540529,0.00004560731,0.00004124444],"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":[0.0003825074,0.00005963277,0.3044232,0.0001186885,0.00009094914,0.000001560737,0.004870165,0.6186166,0.002796603,0.01328812,0.00002886969,0.05532304],"study_design_scores_gemma":[0.0004701384,0.00007557152,0.2242302,0.00001328604,0.00002644876,0.000003527497,0.0003408584,0.7717178,0.00008354181,0.002982161,0.000001545317,0.00005492754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945531,0.0001753232,0.00002304733,0.0001033156,0.00005789807,0.0005280709,0.00001200952,0.000007601106,0.004539646],"genre_scores_gemma":[0.9998627,0.000006567478,0.00003915039,0.0000336623,0.00001770515,0.000003591318,0.000007255187,0.000002170628,0.00002724722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1531012,"threshold_uncertainty_score":0.9895096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07056924466559425,"score_gpt":0.2243477691203778,"score_spread":0.1537785244547835,"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."}}