{"id":"W2796367884","doi":"10.1016/j.jhydrol.2018.04.008","title":"A stacking ensemble learning framework for annual river ice breakup dates","year":2018,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":86,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Environment and Protected Areas","funders":"Alberta Environment and Parks","keywords":"Adaptive neuro fuzzy inference system; Breakup; Computer science; Environmental science; Proxy (statistics); Fuzzy logic; Machine learning; Artificial intelligence; Fuzzy control system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002061065,0.0008598329,0.001061982,0.001515053,0.0006204415,0.001033876,0.001746668,0.00126192,0.002491693],"category_scores_gemma":[0.003060526,0.0005253567,0.001160316,0.001417597,0.000220893,0.001846563,0.001031945,0.001599104,0.001117258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006028848,"about_ca_system_score_gemma":0.001323808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02355121,"about_ca_topic_score_gemma":0.03121953,"domain_scores_codex":[0.9996626,0.00006506913,0.00002476075,0.0001119439,0.00006617083,0.00006944829],"domain_scores_gemma":[0.9990968,0.0003013603,0.00005688708,0.0001460156,0.0003466032,0.00005239994],"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":[0.0001595126,0.0001467896,0.004105899,0.00002990493,0.0002243073,0.00004324978,0.00003649396,0.5852712,0.001464704,0.002122623,0.005479063,0.4009161],"study_design_scores_gemma":[0.000002149736,0.000008595812,0.0003452273,0.000003114679,0.00001319943,0.000004631025,0.000003638565,0.998159,0.0002277942,0.0009655564,0.0002634351,0.000003692334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0913431,0.001369546,0.8998282,0.0004163331,0.0002577626,0.00005504379,0.001587288,0.002939807,0.002202973],"genre_scores_gemma":[0.7264041,0.0007515076,0.2590474,0.0002109635,0.00040715,0.0001622262,0.005882616,0.0003158262,0.006818277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02355121,"threshold_uncertainty_score":0.04682821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01095688713837479,"score_gpt":0.2485471831794575,"score_spread":0.2375902960410827,"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."}}