{"id":"W2336218061","doi":"10.1016/j.dsr.2016.04.008","title":"Improving predictive mapping of deep-water habitats: Considering multiple model outputs and ensemble techniques","year":2016,"lang":"en","type":"article","venue":"Deep Sea Research Part I Oceanographic Research Papers","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Environment Research Council; University of Southampton; Sight Research UK","keywords":"Random forest; Computer science; Statistical model; Range (aeronautics); Redundancy (engineering); Data mining; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001906612,0.001319144,0.001063074,0.001334546,0.0003258112,0.0009609094,0.0009760839,0.00060982,0.0005598771],"category_scores_gemma":[0.004363192,0.000465692,0.001001079,0.001173905,0.0002215953,0.001635626,0.001033321,0.001068163,0.0002045976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003033989,"about_ca_system_score_gemma":0.0004864582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00937061,"about_ca_topic_score_gemma":0.007175112,"domain_scores_codex":[0.9996393,0.0001291026,0.0000243595,0.00008103488,0.0000849129,0.00004128402],"domain_scores_gemma":[0.998246,0.001098007,0.0001581764,0.0001593565,0.0002880583,0.00005046956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005784674,0.00005090571,0.006234604,0.00004000771,0.0001652234,0.00007053592,0.00009720415,0.8381225,0.001792097,0.0007792809,0.0004001847,0.1521896],"study_design_scores_gemma":[0.000001444208,0.00001222017,0.0008091308,0.000006033672,0.00001389335,0.000009167757,0.00001231332,0.9980958,0.0002643764,0.000660429,0.0001093253,0.00000588459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.128961,0.0008412295,0.8671087,0.0002731354,0.00005000705,0.0000300977,0.0001434159,0.001201312,0.001391069],"genre_scores_gemma":[0.8582171,0.0005235092,0.1397986,0.00008101865,0.00006235854,0.00005333015,0.0003413873,0.000135039,0.0007875896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00937061,"threshold_uncertainty_score":0.01863217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.052790183416605,"score_gpt":0.3008414067944512,"score_spread":0.2480512233778462,"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."}}