{"id":"W2097453622","doi":"10.2166/hydro.2011.044","title":"Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data","year":2011,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Multivariate adaptive regression splines; Surface runoff; Watershed; Artificial neural network; Multivariate statistics; Mars Exploration Program; Environmental science; Hydrology (agriculture); Regression analysis; Bayesian multivariate linear regression; Computer science; Machine learning; 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":[0.00092884,0.0002616271,0.0006217171,0.0001220381,0.0001150083,0.00002943062,0.0005654053,0.0001185047,0.00003127383],"category_scores_gemma":[0.0001046623,0.0001537314,0.00007042022,0.000330341,0.0002534306,0.0008543847,0.000131858,0.0004266833,0.000001194404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009001583,"about_ca_system_score_gemma":0.0000279912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007765257,"about_ca_topic_score_gemma":0.0002448773,"domain_scores_codex":[0.9976059,0.00004238324,0.001327608,0.0001670207,0.0004217601,0.000435302],"domain_scores_gemma":[0.9980049,0.0001859892,0.00133935,0.000281159,0.00005811689,0.0001305004],"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":[0.005742378,0.0005142154,0.02833726,0.00008151014,0.00008907138,0.00004632142,0.008143621,0.9469816,0.001611393,0.00001264793,0.00007837067,0.008361587],"study_design_scores_gemma":[0.001501209,0.002500755,0.002331661,0.0003608458,0.00009793763,0.0001790628,0.0004222628,0.9905001,0.001808419,0.00006402359,0.00002284761,0.0002108949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9724242,0.00001144617,0.02683285,0.00006614977,0.00008225055,0.000392773,0.00001376472,0.00001323902,0.000163315],"genre_scores_gemma":[0.8906874,0.000002486081,0.109182,0.00003344493,0.00004149585,0.000002562304,0.00002426368,0.00002128463,0.000005104917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08234912,"threshold_uncertainty_score":0.6268983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1305215527434784,"score_gpt":0.2971876465423763,"score_spread":0.1666660937988979,"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."}}