{"id":"W3169606819","doi":"10.1016/j.jconhyd.2021.103849","title":"Predictive modeling of selected trace elements in groundwater using hybrid algorithms of iterative classifier optimizer","year":2021,"lang":"en","type":"article","venue":"Journal of Contaminant Hydrology","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Wilfrid Laurier University","funders":"","keywords":"Groundwater; Algorithm; Aquifer; Groundwater resources; Computer science; Data mining; Classifier (UML); Artificial neural network; Soil science; Machine learning; Environmental science; Artificial intelligence; Geology","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":[0.0005054838,0.0001552194,0.0005890853,0.0001405115,0.00004771014,0.000009637541,0.0001569586,0.00007333226,0.0002317817],"category_scores_gemma":[0.00006101549,0.000127479,0.0001053437,0.0002611019,0.0001474534,0.0003608276,0.0001211344,0.0002232841,0.000001898095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001767029,"about_ca_system_score_gemma":0.00006288447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043733,"about_ca_topic_score_gemma":0.0001069713,"domain_scores_codex":[0.9979095,0.00026338,0.001026052,0.000198554,0.0003407671,0.000261758],"domain_scores_gemma":[0.9989207,0.0000828575,0.0005775021,0.0001126365,0.0002569864,0.00004927252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002002829,0.002162594,0.3812031,0.00008095887,0.001060768,0.00118756,0.01551528,0.2086464,0.3711183,0.00009065234,0.0001601485,0.0167715],"study_design_scores_gemma":[0.004394013,0.001567693,0.04549711,0.0001495506,0.0002180096,0.00060647,0.001499405,0.8911154,0.05393887,0.0002528311,0.0004834365,0.0002772599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8610162,0.0002015858,0.1382539,0.00008669945,0.0001655251,0.00009415848,0.000007006831,0.000002088806,0.0001728562],"genre_scores_gemma":[0.995731,0.00005540251,0.003865513,0.00004291004,0.00002951834,0.000003513802,0.000003039552,0.00001043083,0.0002586645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.682469,"threshold_uncertainty_score":0.5198441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01892401543348269,"score_gpt":0.2519872618779307,"score_spread":0.2330632464444481,"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."}}