{"id":"W1960909337","doi":"10.1139/s08-041","title":"Modelling nitrogen composition in streams on the Boreal Plain using genetic adaptive general regression neural networks","year":2008,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University; Alberta Health Services; Canadian Natural Resources; University of Alberta","funders":"","keywords":"Watershed; STREAMS; Environmental science; Artificial neural network; Hydrology (agriculture); Regression; Water quality; Mean squared error; Computer science; Ecology; Machine learning; Statistics; Mathematics; Engineering; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0003814649,0.0001294714,0.0001313158,0.00006715241,0.0002588783,0.00002169058,0.0002090395,0.00004118562,0.00001967226],"category_scores_gemma":[0.00001265503,0.0000841662,0.00003841806,0.0001869928,0.0004514488,0.0001884271,0.0001023115,0.0002971278,0.000001288292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002563728,"about_ca_system_score_gemma":0.000005970974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004058413,"about_ca_topic_score_gemma":3.323029e-7,"domain_scores_codex":[0.9988487,0.00003811825,0.0002425331,0.0001852714,0.0004151507,0.0002702418],"domain_scores_gemma":[0.9996127,0.00005852183,0.0001169199,0.00009287901,0.000002086003,0.0001168557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002263353,0.00003444099,0.008202367,4.052088e-7,0.000001671955,0.00005498632,0.0001258785,0.974561,0.01621998,0.000005753521,0.000002609429,0.0007682453],"study_design_scores_gemma":[0.0001491538,0.000170945,0.02457902,0.00003267277,0.000004468182,0.0004167079,0.00001263157,0.9738327,0.0006755522,0.00002979988,0.000003934261,0.00009238361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99007,0.00007335593,0.009644281,0.00003227799,0.00007413376,0.00005985794,0.000001160685,0.000005478099,0.00003939307],"genre_scores_gemma":[0.9923589,0.00004313932,0.007486636,0.00004830251,0.00005129718,7.113941e-7,2.826287e-7,0.000008019875,0.000002713986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01637666,"threshold_uncertainty_score":0.3432198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02063669630692865,"score_gpt":0.1996206030866489,"score_spread":0.1789839067797202,"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."}}