{"id":"W4366263125","doi":"10.1016/j.ecoinf.2023.102107","title":"Non-parametric, semi-parametric, and machine learning models for river temperature frequency analysis at ungauged basins","year":2023,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Bundesamt für Umwelt; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Multivariate adaptive regression splines; Mars Exploration Program; Canonical correlation; Generalized additive model; Random forest; Gradient boosting; Feature selection; Extreme learning machine; Parametric statistics; Computer science; Artificial neural network; Artificial intelligence; Lasso (programming language); Multivariate statistics; Boosting (machine learning); Mean squared error; Machine learning; Mathematics; Regression analysis; Statistics; Nonparametric regression","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966334,0.0002904597,0.0005188737,0.0003678456,0.0006362402,0.0001080855,0.0003275746,0.0003855233,0.0005624708],"category_scores_gemma":[0.001281653,0.0002121911,0.0002070855,0.003761481,0.0003299977,0.0003753096,0.0006126487,0.0005005046,0.0005567933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002991894,"about_ca_system_score_gemma":0.000009078533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000498547,"about_ca_topic_score_gemma":0.00007162829,"domain_scores_codex":[0.9978892,0.00007156198,0.0006298318,0.0003288388,0.0004043185,0.0006762482],"domain_scores_gemma":[0.9982542,0.000946948,0.0002551709,0.0002565264,0.00002765062,0.0002594416],"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":[0.00002168712,0.00007588248,0.09810424,0.00002629498,0.0001093869,0.00001039701,0.0005798696,0.8983113,0.0001617793,0.00008670751,0.001776891,0.0007356127],"study_design_scores_gemma":[0.0003939788,0.000349292,0.06437561,0.000004525631,0.0001569847,0.0000071124,0.00003604939,0.9303086,0.00008635506,0.002454479,0.001530474,0.0002965832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935153,0.00001816407,0.002627536,0.0001804634,0.00007722384,0.0004710843,0.00007975829,0.0003859601,0.002644552],"genre_scores_gemma":[0.9817337,0.00007312697,0.01635621,0.0005724106,0.00002014245,0.0000519119,0.0001696353,0.00001937761,0.001003421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03372863,"threshold_uncertainty_score":0.8652901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03512882131692962,"score_gpt":0.2447943584456639,"score_spread":0.2096655371287343,"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."}}