{"id":"W3142990567","doi":"10.1016/j.watres.2021.117089","title":"Exploration of E. coli contamination drivers in private drinking water wells: An application of machine learning to a large, multivariable, geo-spatio-temporal dataset","year":2021,"lang":"en","type":"article","venue":"Water Research","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Queen's University; Global Institute for Water Security; University of Saskatchewan; Kingston Health Sciences Centre; Public Health Ontario","funders":"","keywords":"Contamination; Aquifer; Hydrogeology; Bivariate analysis; Environmental science; Water well; Groundwater; Bedrock; Univariate; Hydrology (agriculture); Environmental health; Multivariate statistics; Engineering; Statistics; Geology; Ecology; Mathematics; Medicine","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001782346,0.0001049571,0.0001853294,0.0001890457,0.0001708437,0.00003887745,0.0002107647,0.00005690665,0.0003640882],"category_scores_gemma":[0.00004873182,0.00008011858,0.00002054904,0.0003539251,0.00008644586,0.0007388955,0.0005635128,0.0001895972,0.0001419741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001640583,"about_ca_system_score_gemma":0.000009033531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003048229,"about_ca_topic_score_gemma":0.004718444,"domain_scores_codex":[0.9978005,0.000447675,0.0003646283,0.0003754396,0.0006372613,0.0003744513],"domain_scores_gemma":[0.999458,0.00002745006,0.00004967342,0.00027843,0.0001235871,0.00006287905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001071233,0.0003660666,0.3883656,0.00005408395,0.00001746438,0.0000115384,0.01882269,0.004748373,0.5803939,0.0002003931,0.0001371391,0.006775638],"study_design_scores_gemma":[0.001283925,0.0002343679,0.09157474,0.00004231896,0.000008724238,0.00000111325,0.002564301,0.02703201,0.7762917,0.0003206182,0.1004325,0.000213656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9724173,0.000005472989,0.02658743,0.0003259807,0.00002461712,0.0004575059,0.0000512104,0.00001175416,0.0001187491],"genre_scores_gemma":[0.9944522,0.000009260715,0.0006565389,0.00003002809,0.00001185992,0.0001231811,0.003886161,0.0000126112,0.0008181194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2967909,"threshold_uncertainty_score":0.460803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04510934528432027,"score_gpt":0.320124583976891,"score_spread":0.2750152386925707,"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."}}