{"id":"W3196416365","doi":"10.5194/hess-25-4947-2021","title":"Development of a Wilks feature importance method with improved variable rankings for supporting hydrological inference and modelling","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Regina","funders":"National Key Research and Development Program of China; Western Economic Diversification Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Random forest; Inference; Feature selection; Feature (linguistics); Variable (mathematics); Statistic; Computer science; Resampling; Machine learning; Environmental science; Statistics; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003378605,0.0007207511,0.001000046,0.002529205,0.0005165964,0.0008394119,0.001397266,0.0006829105,0.001523869],"category_scores_gemma":[0.009349505,0.0003957474,0.0009312494,0.001331922,0.0004958683,0.001325967,0.0008674254,0.001226438,0.0003775197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006731334,"about_ca_system_score_gemma":0.001866363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004686329,"about_ca_topic_score_gemma":0.005581711,"domain_scores_codex":[0.9986836,0.0005089801,0.00009017862,0.0001826782,0.0004471484,0.00008744071],"domain_scores_gemma":[0.9959288,0.002051069,0.0002945264,0.0002473396,0.001337637,0.0001405922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002213896,0.000248163,0.009668231,0.0001867376,0.0001618612,0.0001997681,0.0001323586,0.4602327,0.01285407,0.01583623,0.003067425,0.4971911],"study_design_scores_gemma":[0.00000804216,0.00002101055,0.0004009263,0.000003494376,0.000006673101,0.0000106001,0.00000473815,0.9967545,0.0009262112,0.001557777,0.0002992738,0.000006825358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01000725,0.00004645291,0.9891555,0.00003529876,0.00001782378,0.00004561491,0.00005374709,0.0003803083,0.0002580239],"genre_scores_gemma":[0.2961791,0.00009093017,0.7018598,0.0000716816,0.00008979996,0.0002541862,0.0004626274,0.0001235066,0.0008683638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004686329,"threshold_uncertainty_score":0.01786798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01986555532236984,"score_gpt":0.2511149198846641,"score_spread":0.2312493645622943,"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."}}