{"id":"W1562601998","doi":"10.1023/a:1005165315197","title":"The Application of Artificial Neural Networks for the Prediction of Water Quality of Polluted Aquifer","year":2000,"lang":"en","type":"article","venue":"Water Air & Soil Pollution","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Groundwater; Term (time); Environmental science; Long-term prediction; Artificial neural network; Petroleum engineering; Hydrology (agriculture); Computer science; Engineering; Geotechnical engineering; Machine learning","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":[0.0005618231,0.0000940933,0.0001400162,0.00001496861,0.0002713171,0.000007938413,0.0001567299,0.00005398569,0.00007162439],"category_scores_gemma":[0.000005183405,0.00004271701,0.0001012198,0.00007889693,0.0003370325,0.0001195578,0.00005192512,0.00005020266,0.00001368443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004061012,"about_ca_system_score_gemma":0.000002252837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008440518,"about_ca_topic_score_gemma":0.0004143532,"domain_scores_codex":[0.9988365,0.00009099627,0.0004743567,0.0001523585,0.0002390929,0.0002066979],"domain_scores_gemma":[0.9995676,0.00004405606,0.00009633067,0.0002405176,0.00003401209,0.00001742722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007595251,0.0002040188,0.01001718,0.00003205445,0.0001093451,5.444542e-8,0.003990482,0.09246804,0.3020027,0.0004003389,0.0005701092,0.5894462],"study_design_scores_gemma":[0.0007545434,0.0002072793,0.4692372,0.000008331685,0.0001084136,0.000001361567,0.0004523643,0.1797043,0.3394052,0.0008967411,0.009060223,0.0001640459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9372956,0.00003058442,0.06066014,0.001306519,0.0001352715,0.0004119337,0.00003376492,0.00001477734,0.0001114551],"genre_scores_gemma":[0.9989015,0.00001130831,0.00001699334,0.00006138672,0.00006962883,0.00008498257,0.00002839903,0.000006788766,0.0008190026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5892821,"threshold_uncertainty_score":0.2086779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01535984969971896,"score_gpt":0.2361554236364156,"score_spread":0.2207955739366967,"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."}}