{"id":"W2093593153","doi":"10.1016/j.envpol.2013.04.028","title":"Application of fingerprint-based multivariate statistical analyses in source characterization and tracking of contaminated sediment migration in surface water","year":2013,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Toxic Organic Pollutants Impact","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Natural Sciences and Engineering Research Council","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contamination; Multivariate statistics; Principal component analysis; Sediment; Environmental science; Fingerprint (computing); Source tracking; Environmental chemistry; Multivariate analysis; Linear discriminant analysis; Geology; Chemistry; Ecology; Computer science; Statistics; Biology; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009654509,0.000291474,0.0002589982,0.001435876,0.0002391274,0.0005104226,0.0002020371,0.0002896909,0.0003397486],"category_scores_gemma":[0.002271718,0.0001314473,0.0003376851,0.001247808,0.0001763008,0.0003217192,0.0003028639,0.0003400573,0.0001202569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001510797,"about_ca_system_score_gemma":0.0003442258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002248385,"about_ca_topic_score_gemma":0.002447583,"domain_scores_codex":[0.999711,0.0001125153,0.00002000478,0.00006819177,0.00006641319,0.00002186596],"domain_scores_gemma":[0.9989533,0.0005514689,0.0001765119,0.00007790353,0.0002049513,0.00003588533],"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":[0.0008026421,0.0004191507,0.1744754,0.0002324366,0.0002915201,0.0001372515,0.0002635925,0.03029096,0.3847308,0.001169711,0.0005127941,0.4066737],"study_design_scores_gemma":[0.0000515873,0.0008513248,0.2616359,0.00002695615,0.0003995882,0.0007136915,0.000331227,0.5720512,0.1595934,0.002195319,0.002019132,0.0001307733],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7929361,0.0006271467,0.2044394,0.00007344482,0.0000323475,0.00004192761,0.000552159,0.000427698,0.0008697713],"genre_scores_gemma":[0.9420751,0.0001993363,0.05712068,0.00001521052,0.00001330546,0.00002443047,0.000159442,0.00002608121,0.0003664884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002248385,"threshold_uncertainty_score":0.005105853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009297404791622624,"score_gpt":0.2380157502968663,"score_spread":0.2287183455052437,"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."}}