{"id":"W2174882701","doi":"10.1139/cjfr-2014-0562","title":"Random forests and stochastic gradient boosting for predicting tree canopy cover: comparing tuning processes and model performance","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":212,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Forest Service","keywords":"Random forest; Gradient boosting; Canopy; Statistics; Tree canopy; Tree (set theory); Mean squared error; Mathematics; Computer science; Machine learning; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001663961,0.0001242718,0.000216888,0.0001698781,0.0005098437,0.0001763858,0.0002135774,0.00006080855,0.000002345089],"category_scores_gemma":[0.001774318,0.00009701267,0.00002368767,0.0002711053,0.000370312,0.0003742945,0.00006894262,0.0003961167,0.000001681138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004486653,"about_ca_system_score_gemma":0.0006355018,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002958863,"about_ca_topic_score_gemma":0.1432039,"domain_scores_codex":[0.9984056,0.00005188629,0.0002742021,0.0001944252,0.0004787107,0.0005952116],"domain_scores_gemma":[0.9982337,0.0002809071,0.0001299082,0.00009486674,0.0002366867,0.001023918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009610662,0.000005096903,0.6931567,0.0000628663,0.00001110395,0.00001916926,0.002294167,0.3012604,0.0000924428,0.00001079059,0.001228245,0.001763002],"study_design_scores_gemma":[0.001887133,0.0003849781,0.1603161,0.0004394058,0.00002021012,0.0004958833,0.0006439731,0.8346184,0.0000785065,0.0006977238,0.0002531573,0.0001646003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933987,0.0004230224,0.004497303,0.0002060443,0.00006736271,0.0003181677,0.000004033005,0.000004939924,0.001080406],"genre_scores_gemma":[0.997475,0.00001362481,0.002212317,0.00001393855,0.0001001095,0.00000263806,0.000001990583,0.00001591189,0.0001644447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.533358,"threshold_uncertainty_score":0.8724304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06001537515838437,"score_gpt":0.2812514193327904,"score_spread":0.221236044174406,"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."}}