{"id":"W2170240781","doi":"10.1016/j.watres.2010.05.019","title":"Novel application of a statistical technique, Random Forests, in a bacterial source tracking study","year":2010,"lang":"en","type":"article","venue":"Water Research","topic":"Fecal contamination and water quality","field":"Environmental Science","cited_by":82,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Texas Department of State Health Services; Texas General Land Office; National Oceanic and Atmospheric Administration; Canadian Centre for Applied Research in Cancer Control","keywords":"Random forest; Linear discriminant analysis; Sampling (signal processing); Environmental science; Veterinary medicine; Mathematics; Statistics; Biology; Physics; Artificial intelligence; Medicine; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006300285,0.000586568,0.0006138351,0.0008552709,0.0006119093,0.0007258671,0.0007472827,0.0007528045,0.000576706],"category_scores_gemma":[0.007433194,0.0003876021,0.0007147163,0.0009225577,0.0004346709,0.0006406158,0.0007544711,0.0007392949,0.0002212415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001196623,"about_ca_system_score_gemma":0.0006423655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001411822,"about_ca_topic_score_gemma":0.003414031,"domain_scores_codex":[0.9980093,0.001197356,0.00006760703,0.0003278715,0.0003204597,0.00007744873],"domain_scores_gemma":[0.9954416,0.003308964,0.0002429054,0.0003652508,0.0004799357,0.0001613642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00153555,0.0007899946,0.05344718,0.0002818674,0.0005549178,0.0005396687,0.0003780108,0.09912498,0.3174006,0.006970053,0.001696233,0.5172811],"study_design_scores_gemma":[0.00007663461,0.0004898214,0.01706616,0.00002056223,0.0002161623,0.0007709322,0.00008424558,0.9234472,0.04630658,0.009113131,0.00231641,0.00009216319],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06046727,0.0001512612,0.9385468,0.00007993841,0.0000559462,0.00003833955,0.0000758095,0.0002709902,0.0003135732],"genre_scores_gemma":[0.27682,0.0001512245,0.7221497,0.00005933366,0.00007954864,0.00008682976,0.000126024,0.0001060803,0.0004212566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006300285,"threshold_uncertainty_score":0.03331947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059769811739862,"score_gpt":0.3717241681816979,"score_spread":0.3211264700642993,"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."}}