{"id":"W4408948502","doi":"10.3389/fenvs.2025.1543852","title":"Regression-based machine learning models for nitrate and chloride prediction in surface water in a small agricultural sand plain sub-watershed in southwestern Ontario, Canada","year":2025,"lang":"en","type":"article","venue":"Frontiers in Environmental Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; Université du Québec à Montréal; University of Guelph","funders":"","keywords":"Watershed; Nitrate; Agriculture; Hydrology (agriculture); Environmental science; Surface water; Geology; Machine learning; Geography; Archaeology; Environmental engineering; Ecology; Geotechnical engineering; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0009191565,0.0002217793,0.0002503545,0.0001402859,0.0001616716,0.00004364409,0.0002893253,0.0001000537,0.00004094768],"category_scores_gemma":[0.00002895668,0.0001613961,0.00002217891,0.0003749805,0.0004815791,0.0003197813,0.0002133233,0.0003950916,0.000001475007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002941603,"about_ca_system_score_gemma":0.00006340969,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5549942,"about_ca_topic_score_gemma":0.8774965,"domain_scores_codex":[0.9978803,0.00008940791,0.0003692743,0.0007041004,0.0002887574,0.0006681082],"domain_scores_gemma":[0.9996696,0.00004465703,0.00005739123,0.0001274114,0.000001310749,0.00009969676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000942929,0.00003901772,0.5608221,0.000004215072,6.58149e-7,0.00001117739,0.0005434193,0.4212218,0.01697439,2.653748e-7,0.00001361966,0.0002749754],"study_design_scores_gemma":[0.001172474,0.00005783339,0.5607667,0.00008452022,0.00000268326,0.000001729612,0.0001637706,0.4231342,0.0141422,0.0002303861,0.00005292847,0.0001905453],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998431,0.00003133471,0.0004494925,0.0001985299,0.0001845218,0.0004858946,0.00001504544,0.00001161557,0.0001925799],"genre_scores_gemma":[0.9980899,0.000006069778,0.001390914,0.0001196122,0.000003535247,0.00003602,0.00003475479,0.000007650431,0.0003115478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3225023,"threshold_uncertainty_score":0.769219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008898137932366561,"score_gpt":0.1744443739821476,"score_spread":0.165546236049781,"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."}}