{"id":"W2256317226","doi":"10.2166/hydro.2013.042","title":"Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes","year":2013,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Streamflow; Lead time; Environmental science; Watershed; Overfitting; Computer science; Wavelet; Artificial neural network; Climatology; Meteorology; Statistics; Econometrics; Mathematics; Artificial intelligence; Machine learning; Geology; Drainage basin; Geography; Engineering","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":[0.002593166,0.0002551054,0.0005484725,0.0001516083,0.0002130282,0.0001485237,0.0008443302,0.0001304898,0.0002441146],"category_scores_gemma":[0.001337691,0.0001980658,0.000103514,0.0003761995,0.0002068739,0.002038477,0.0007300088,0.0006150469,0.00009516024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002364749,"about_ca_system_score_gemma":0.00004477862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002088017,"about_ca_topic_score_gemma":0.00003136523,"domain_scores_codex":[0.9969276,0.0001465055,0.001620779,0.0001851413,0.0004668338,0.0006532085],"domain_scores_gemma":[0.9974841,0.0004410169,0.001384488,0.0004307054,0.00004031489,0.0002193254],"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":[0.00001952381,0.0001185551,0.01943472,0.0000664463,0.000032557,0.00005667889,0.001153157,0.9488384,0.005479082,0.000001433842,0.0002786066,0.02452087],"study_design_scores_gemma":[0.0007855253,0.0001256547,0.001902036,0.0002551443,0.00004175094,0.0005172184,0.0002419607,0.9954339,0.0002063424,0.00004517255,0.0002281364,0.0002171938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9476068,0.00001716134,0.05077368,0.00006580169,0.0002008159,0.0002426141,0.000008110556,0.00002161803,0.001063411],"genre_scores_gemma":[0.3870282,0.00000782029,0.6127673,0.0001033007,0.00005831386,9.368824e-7,0.000004236057,0.00001704735,0.00001283285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5619937,"threshold_uncertainty_score":0.8076888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1080515716221514,"score_gpt":0.3563714897035554,"score_spread":0.248319918081404,"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."}}