{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001602546,0.0001357994,0.0001645374,0.00001699615,0.0004725461,0.00002177455,0.0008104315,0.00002937552,0.0004019099],"category_scores_gemma":[0.0001790035,0.00006699941,0.00008852407,0.0002130936,0.002302472,0.000216969,0.001500488,0.0002433261,0.00003263846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000152305,"about_ca_system_score_gemma":0.00001169392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006729644,"about_ca_topic_score_gemma":3.23198e-7,"domain_scores_codex":[0.9978758,0.0001135828,0.0003619564,0.0003631842,0.0009530243,0.000332489],"domain_scores_gemma":[0.999238,0.00004187567,0.0002940189,0.000328929,0.000004021527,0.00009322643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007611498,0.000028131,0.0004591701,0.000004497088,0.000002976794,1.187051e-7,0.0005413449,0.4146618,0.5835908,0.000004181886,7.504845e-7,0.0006985574],"study_design_scores_gemma":[0.0001497047,0.00012573,0.009547941,0.000009265718,0.0000234338,0.00001018202,0.00005553366,0.6319755,0.3579108,0.00007379623,0.00002998207,0.00008816118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970371,0.00001004558,0.001699542,0.0006310502,0.00009903923,0.0001968654,0.00002174572,0.00001951739,0.0002851084],"genre_scores_gemma":[0.997354,0.000001836823,0.002505713,0.00004609431,0.0000271204,0.000002275829,0.000001107624,0.000008709714,0.0000530957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2256801,"threshold_uncertainty_score":0.8483555,"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."}}