{"id":"W2543805200","doi":"10.1007/s00477-016-1338-z","title":"Comparison of machine learning models for predicting fluoride contamination in groundwater","year":2016,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Fluoride; Extreme learning machine; Groundwater; Support vector machine; Contamination; Multilayer perceptron; Environmental science; Artificial neural network; Groundwater contamination; Machine learning; Computer science; Artificial intelligence; Chemistry; Geology; Geotechnical engineering; Ecology; Aquifer","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":[0.001617356,0.0001082903,0.0001922049,0.0001807245,0.0002422138,0.00004257191,0.0002340109,0.00004725833,0.000008203149],"category_scores_gemma":[0.0001170578,0.00007404768,0.00002916185,0.00008455905,0.0001345398,0.0003050864,0.0002867928,0.0002695599,0.000002350189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001707948,"about_ca_system_score_gemma":0.00002568814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002475384,"about_ca_topic_score_gemma":0.00005768196,"domain_scores_codex":[0.9982575,0.0002296957,0.0002837961,0.0003508612,0.000506835,0.0003712931],"domain_scores_gemma":[0.9987055,0.0008968911,0.000108706,0.0001743043,0.00001956182,0.00009505415],"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":[0.00009472134,0.0006472283,0.623519,0.00004479351,0.00003824615,0.000002338577,0.001612395,0.01556851,0.004632186,0.008051297,0.00001417557,0.3457751],"study_design_scores_gemma":[0.001248192,0.001297011,0.08742294,0.00007580858,0.000004669034,0.000001768783,0.0002378013,0.9022772,0.0003877194,0.006874724,0.00007284805,0.00009931453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4081043,0.0001221714,0.5912723,0.0001492378,0.00002852193,0.000232415,0.000007148172,0.00001423212,0.00006966798],"genre_scores_gemma":[0.9916812,0.0001500871,0.007720891,0.000002403926,0.00002323937,0.00007698387,0.000008726453,0.000009892399,0.0003266284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8867087,"threshold_uncertainty_score":0.3019577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04133773012840797,"score_gpt":0.3588003674862326,"score_spread":0.3174626373578247,"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."}}