{"id":"W4385348544","doi":"10.1111/mice.13074","title":"A hybrid ontology‐based semantic and machine learning model for the prediction of spring breakup","year":2023,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Breakup; Flooding (psychology); Computer science; Feature selection; Scale (ratio); Ontology; Variable (mathematics); Machine learning; Random forest; Model selection; Artificial intelligence; Data mining; Geography; Mathematics; Cartography","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":[0.0001313232,0.0001280528,0.0001644547,0.00009541222,0.0001318616,0.00003693553,0.0000805902,0.00004270775,0.00003116673],"category_scores_gemma":[0.00001833043,0.000094306,0.00003553854,0.00009771932,0.00003355597,0.00008646785,0.00002524853,0.0001400867,7.311673e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002283596,"about_ca_system_score_gemma":0.000009199891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002594099,"about_ca_topic_score_gemma":0.0005223327,"domain_scores_codex":[0.9993843,0.000009609368,0.0001539323,0.0001722773,0.000077323,0.000202586],"domain_scores_gemma":[0.9995325,0.0002609101,0.00004467575,0.00008793051,0.00001907782,0.00005491344],"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":[0.00001223182,0.000001134141,0.1064263,0.0001764175,0.00001911951,0.000002160423,0.0002598621,0.8793002,0.0005502939,0.00001863127,0.0000885074,0.0131451],"study_design_scores_gemma":[0.0002161241,0.00004901188,0.2807391,0.00003306349,0.00001558721,0.00001620506,0.00000942792,0.7184205,0.00004772617,0.00008208229,0.0003077535,0.00006341868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7471554,0.0007025101,0.2510909,0.0001011099,0.0002880707,0.0001559706,0.0003925978,0.00009782543,0.00001566058],"genre_scores_gemma":[0.9979482,0.0002008465,0.001422164,0.00005014479,0.0001482175,0.000002432665,0.0002125504,0.000006754281,0.000008705022],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2507928,"threshold_uncertainty_score":0.3845687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01879461820224626,"score_gpt":0.1915811950814181,"score_spread":0.1727865768791719,"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."}}