{"id":"W2081670007","doi":"10.1029/2010wr009945","title":"Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada","year":2011,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":490,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Autoregressive integrated moving average; Artificial neural network; Mean squared error; Wavelet; Autoregressive model; Linear regression; Statistics; Econometrics; Demand forecasting; Moving average; Computer science; Environmental science; Meteorology; Mathematics; Time series; Artificial intelligence; Geography; Operations research","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":[0.0030722,0.0003359478,0.0006210255,0.0001160978,0.0006678123,0.00009414524,0.0003716139,0.0002224847,0.0001419671],"category_scores_gemma":[0.0005718917,0.0002004128,0.00006026119,0.000292548,0.0007446467,0.0001663826,0.0008530014,0.0008117874,0.000003201098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001317913,"about_ca_system_score_gemma":0.00002033356,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.175667,"about_ca_topic_score_gemma":0.2426257,"domain_scores_codex":[0.9952186,0.00115473,0.0008275112,0.0007620599,0.0005224287,0.001514641],"domain_scores_gemma":[0.9984019,0.0007838947,0.0001449015,0.0002954837,0.00008453887,0.00028926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002584414,0.0002510425,0.4592338,0.0001246893,0.00005576419,0.0001555971,0.02427887,0.4033152,0.01937119,0.000004177864,0.001629889,0.08899539],"study_design_scores_gemma":[0.000375196,0.0003483288,0.00879173,0.0001023197,0.00001332813,0.00001316745,0.0002021613,0.9671481,0.02037602,0.0004334391,0.001936352,0.0002598648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982603,0.0001349335,0.0004480002,0.0001680254,0.0001359766,0.0006703013,0.00001471821,0.0000299745,0.0001377306],"genre_scores_gemma":[0.9830372,0.000003602644,0.01634561,0.00004190345,0.0002843059,0.00004649918,0.00004613414,0.0000441476,0.0001505389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5638329,"threshold_uncertainty_score":0.8298223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1257209807763414,"score_gpt":0.3559706911852541,"score_spread":0.2302497104089127,"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."}}