{"id":"W7117356171","doi":"10.1016/j.wroa.2025.100478","title":"Transferable soft-sensors for predicting nitrate in diverse watersheds","year":2025,"lang":"en","type":"article","venue":"Water Research X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"South East Water","keywords":"Nitrate; Transferability; Artificial neural network; Linear regression; Data point; Training set; Aquatic ecosystem","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":[0.002183954,0.0001016397,0.0001311758,0.0001299109,0.0003183418,0.0000677015,0.0003122726,0.00009040747,0.0006704752],"category_scores_gemma":[0.0001724714,0.00006823652,0.00004764092,0.0003251647,0.0002872231,0.0001390699,0.0002298307,0.0003449745,0.0003434021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001966048,"about_ca_system_score_gemma":0.00001040849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001065001,"about_ca_topic_score_gemma":0.0002194238,"domain_scores_codex":[0.998,0.0001996608,0.0001939835,0.0003850255,0.0003328439,0.0008884309],"domain_scores_gemma":[0.9995782,0.0001250952,0.000006297417,0.0001882012,0.00001696912,0.00008520131],"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":[0.0008278309,0.0003850506,0.3897004,0.0002080073,0.00004403358,0.0001381494,0.007285204,0.100845,0.4766003,0.0002538831,0.006461453,0.01725065],"study_design_scores_gemma":[0.004449021,0.001020454,0.01979169,0.0003188121,0.00002682342,0.00000895408,0.0005782875,0.2743377,0.5965374,0.04471259,0.05744373,0.0007745303],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987482,0.000004251017,0.0002943072,0.001633793,0.00007220447,0.000468258,0.000005417594,0.00005428896,0.009985557],"genre_scores_gemma":[0.9925044,0.000002865317,0.0004101442,0.0001030865,0.00001989567,0.00008088963,0.000007852087,0.00001045917,0.006860383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3699087,"threshold_uncertainty_score":0.7341233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07853795755210921,"score_gpt":0.3460346891128839,"score_spread":0.2674967315607747,"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."}}