{"id":"W4224315380","doi":"10.1016/j.envsoft.2022.105402","title":"Machine-learning approach for predicting the occurrence and timing of mid-winter ice breakups on canadian rivers","year":2022,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Environment and Climate Change Canada; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; Environment and Climate Change Canada","keywords":"Computer science; Robustness (evolution); Probabilistic logic; Machine learning; Preprocessor; Scale (ratio); Model selection; Data mining; Artificial intelligence; Geography; Cartography","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":[0.0004828211,0.0001956282,0.0001675064,0.00004366428,0.00114861,0.00002147209,0.0003381855,0.00005147147,0.00047477],"category_scores_gemma":[0.00004970452,0.0001663621,0.00008008704,0.00009669076,0.0002959276,0.00008241589,0.0003531224,0.0004641816,0.00001016053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003808008,"about_ca_system_score_gemma":0.000009719171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005582607,"about_ca_topic_score_gemma":0.0001079595,"domain_scores_codex":[0.9983962,0.0001160844,0.0002319556,0.0004883596,0.0003587982,0.0004085591],"domain_scores_gemma":[0.9992881,0.0002231199,0.0001381533,0.0002040737,0.000001371263,0.0001451734],"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":[0.00003174664,0.00004680404,0.04700565,0.000009133986,0.00001001162,0.000002189801,0.001365624,0.9466549,0.0001166959,0.000002486647,0.00005537093,0.004699366],"study_design_scores_gemma":[0.0002658812,0.0002504862,0.0008069588,0.00001556171,0.00003058427,0.00002063382,0.0002470118,0.9950206,0.0001143603,0.0001236829,0.002890762,0.0002134307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9462894,0.0001424883,0.05188,0.00009865905,0.00009818437,0.0004769617,0.000359178,0.00006100928,0.0005941063],"genre_scores_gemma":[0.9883577,0.00001299324,0.01105779,0.0002522498,0.00001795154,0.00005833396,0.0000923242,0.00002433499,0.0001263404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04836573,"threshold_uncertainty_score":0.8834299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02385358181453426,"score_gpt":0.203775625469272,"score_spread":0.1799220436547377,"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."}}