{"id":"W2070424919","doi":"10.1016/j.cageo.2012.06.023","title":"Nonlinear regression in environmental sciences by support vector machines combined with evolutionary strategy","year":2012,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Support vector machine; Random forest; Artificial neural network; Benchmark (surveying); Computer science; Regression; Artificial intelligence; Machine learning; Feature selection; Decision tree; Evolutionary algorithm; Linear regression; Tree (set theory); Data mining; Statistics; Mathematics","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":[0.0006149843,0.0002231729,0.000192642,0.00006919554,0.0004375971,0.00006476323,0.0006049998,0.00006591155,0.000721533],"category_scores_gemma":[0.0000191066,0.0001450712,0.00003517406,0.000558547,0.001963722,0.0007203913,0.0003151326,0.0001649539,0.0001825162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384913,"about_ca_system_score_gemma":0.00002448808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002932492,"about_ca_topic_score_gemma":0.00002955194,"domain_scores_codex":[0.9977388,0.0001090005,0.0002398512,0.0005281851,0.0006779886,0.0007062035],"domain_scores_gemma":[0.9994056,0.00009540893,0.000116284,0.0001678583,0.000002144794,0.0002126527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004789087,0.0006300315,0.9698945,0.000004081008,0.000003121666,0.00001424402,0.0003930207,0.01025827,0.004677136,0.00003533689,0.003672096,0.01037026],"study_design_scores_gemma":[0.0008001733,0.002820607,0.7279499,0.00006688615,0.00001150736,0.000115796,0.0001382618,0.2598963,0.0007986701,0.0002601288,0.006400271,0.0007414908],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972672,0.0001069633,0.0002952101,0.0003324426,0.0003055242,0.0001666945,0.00001381986,0.00006133277,0.001450798],"genre_scores_gemma":[0.9901477,0.00000850294,0.009288656,0.0002728738,0.00004963176,0.000007974667,0.00001937349,0.000007953159,0.0001973009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.249638,"threshold_uncertainty_score":0.790028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01556180750645817,"score_gpt":0.2389371640800252,"score_spread":0.2233753565735671,"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."}}