{"id":"W3009964072","doi":"10.1016/j.scitotenv.2020.137612","title":"Improving prediction of water quality indices using novel hybrid machine-learning algorithms","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":426,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Random forest; Pruning; Water quality; Algorithm; Statistics; Mean squared error; Computer science; Pearson product-moment correlation coefficient; Decision tree; Tree (set theory); Data mining; Mathematics; Machine learning; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008136216,0.0006642738,0.0007371384,0.0006489207,0.00027361,0.0007762364,0.0008563187,0.0007236907,0.0006969131],"category_scores_gemma":[0.001776855,0.0002549658,0.0005192665,0.0006739875,0.0002616701,0.0008429327,0.0004233596,0.0006650299,0.0002286427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003633855,"about_ca_system_score_gemma":0.0004669226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004407315,"about_ca_topic_score_gemma":0.004411263,"domain_scores_codex":[0.9997301,0.00006343117,0.00002248426,0.0000677068,0.00008606432,0.00003017836],"domain_scores_gemma":[0.9991014,0.0004761652,0.00006841106,0.00005706878,0.0002707718,0.00002628432],"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":[0.0001970478,0.0002713426,0.003439541,0.00006728901,0.0001862635,0.00004831555,0.00003361043,0.7658952,0.009996222,0.001620694,0.001158748,0.2170857],"study_design_scores_gemma":[0.0000034264,0.0000111672,0.0001773497,7.064265e-7,0.000004929439,0.000002991981,9.646703e-7,0.9991109,0.000505837,0.0001290073,0.00005103561,0.000001651579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1727668,0.0007937212,0.822269,0.0001929626,0.0002278991,0.00004564293,0.00007618608,0.000940581,0.00268722],"genre_scores_gemma":[0.8535424,0.0002297557,0.1442834,0.00008391769,0.0001077204,0.0000608218,0.0001682884,0.00003684725,0.001486787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004407315,"threshold_uncertainty_score":0.008763313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03510598550374761,"score_gpt":0.2329694438179496,"score_spread":0.197863458314202,"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."}}