{"id":"W2113332887","doi":"10.1890/11-0252.1","title":"Gradient forests: calculating importance gradients on physical predictors","year":2011,"lang":"en","type":"article","venue":"Ecology","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":544,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bedford Institute of Oceanography; Fisheries and Oceans Canada","funders":"Fisheries and Oceans Canada; Commonwealth Scientific and Industrial Research Organisation; Alfred P. Sloan Foundation","keywords":"Environmental gradient; Biodiversity; Range (aeronautics); Random forest; Ecology; Environmental science; Univariate; Beta diversity; Abundance (ecology); Sampling (signal processing); Gradient analysis; Forest inventory; Geography; Physical geography; Multivariate statistics; Forest management; Statistics; Mathematics; Biology; Computer science; Ordination; Habitat","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":[0.003451615,0.001071048,0.0009248322,0.003209458,0.0004845583,0.0009431173,0.0008132341,0.0006102674,0.001516267],"category_scores_gemma":[0.01230569,0.0006521369,0.0008963114,0.002003127,0.0005437207,0.001554792,0.001057208,0.0009058983,0.000569796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004307525,"about_ca_system_score_gemma":0.001154954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009871649,"about_ca_topic_score_gemma":0.01144744,"domain_scores_codex":[0.9989924,0.0004214501,0.00007788102,0.0001892936,0.0002144728,0.000104464],"domain_scores_gemma":[0.9958085,0.002887835,0.0002830208,0.0003164702,0.0005948968,0.0001093281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006577853,0.0002288294,0.05868258,0.0004449028,0.0003580549,0.0002591264,0.000366319,0.3378813,0.006679229,0.01473981,0.005122361,0.5745796],"study_design_scores_gemma":[0.00005350938,0.0000990698,0.01137741,0.00006793032,0.00004971168,0.0001669303,0.00006733595,0.9637313,0.002884075,0.01866701,0.002789701,0.00004592198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04668903,0.0003825988,0.9498427,0.00004592008,0.00003522679,0.0001501794,0.0005948026,0.001593332,0.0006663188],"genre_scores_gemma":[0.3686529,0.0004095072,0.6269316,0.00008575808,0.00009267126,0.0004469092,0.002082488,0.0004314633,0.0008666018],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009871649,"threshold_uncertainty_score":0.01962841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0308317147254162,"score_gpt":0.2433215238192842,"score_spread":0.212489809093868,"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."}}