{"id":"W7117166872","doi":"10.1016/j.wroa.2025.100475","title":"Using “big data” and non-linear machine learning to infer groundwater contamination mechanisms across a spatially extensive, geologically heterogeneous region","year":2025,"lang":"en","type":"article","venue":"Water Research X","topic":"Fecal contamination and water quality","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Aquifer; Groundwater; Hydrology (agriculture); Contamination; Groundwater recharge; Water quality; Hydrogeology; Fecal coliform","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002377751,0.0001732207,0.000207265,0.0001123803,0.000567512,0.0001973624,0.0004600655,0.0001206945,0.0001541036],"category_scores_gemma":[0.0002577936,0.0001209058,0.00002925033,0.0002328892,0.0002476719,0.0002852922,0.002723751,0.0003795484,0.0002240701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001970183,"about_ca_system_score_gemma":0.00001388787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003616686,"about_ca_topic_score_gemma":0.001497375,"domain_scores_codex":[0.9971782,0.0005833487,0.000300275,0.0007068178,0.0005668209,0.000664567],"domain_scores_gemma":[0.9991364,0.00007509585,0.00003197126,0.0004754118,0.0001135135,0.0001676483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009868868,0.000484225,0.1472867,0.0001880399,0.0001099651,0.000715597,0.01095014,0.005987778,0.6759611,0.0003264032,0.0004971966,0.156506],"study_design_scores_gemma":[0.003894062,0.001914716,0.1934611,0.0002239807,0.00004940692,0.0001275262,0.0007686961,0.4247924,0.3039669,0.008724104,0.06074734,0.001329867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8876152,0.00000799976,0.1099135,0.001473513,0.0001002572,0.0005055296,0.000007165198,0.00003831972,0.0003385677],"genre_scores_gemma":[0.9935213,0.00001063595,0.001580461,0.0007551952,0.00003547023,0.00002581121,0.00009535008,0.00001530013,0.003960517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4188046,"threshold_uncertainty_score":0.5467371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1654134129102717,"score_gpt":0.3896354168105627,"score_spread":0.2242220039002911,"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."}}