{"id":"W4396931861","doi":"10.1007/s10980-024-01903-2","title":"Machine learning allows for large-scale habitat prediction of a wide-ranging carnivore across diverse ecoregions","year":2024,"lang":"en","type":"article","venue":"Landscape Ecology","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"BP (Canada)","funders":"Rocky Mountain Research Station; U.S. Forest Service; California Department of Fish and Wildlife; Washington Department of Fish and Wildlife; Summerlee Foundation; U.S. Department of Agriculture","keywords":"Carnivore; Landscape ecology; Ranging; Habitat; Scale (ratio); Nature Conservation; Ecology; Geography; Environmental science; Cartography; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003574218,0.0001020169,0.0001603483,0.00003989559,0.000267491,0.00001241143,0.0001087774,0.0001525747,0.0008642257],"category_scores_gemma":[0.0001247599,0.00009541516,0.00009088135,0.0001557352,0.00007781574,0.0001602272,0.0001101584,0.0001698447,0.0001310269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005479632,"about_ca_system_score_gemma":0.00001554628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000496807,"about_ca_topic_score_gemma":0.007830381,"domain_scores_codex":[0.9990746,0.00006082315,0.000193438,0.000277421,0.00007183271,0.0003218444],"domain_scores_gemma":[0.9993576,0.0004165936,0.0000631323,0.0001072483,0.00001078604,0.00004467869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000351122,0.00004347578,0.9872368,0.00002758071,0.00003040898,0.000007134615,0.001585343,0.002587944,0.0001327829,0.0001234673,0.007740639,0.0004493072],"study_design_scores_gemma":[0.0005440095,0.0002237127,0.8415819,0.00001207379,0.00004508093,0.00001285161,0.0006025949,0.1230624,0.00002223801,0.0003503129,0.03345276,0.00008998831],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993734,0.00009433794,0.003000301,0.0008933547,0.0007069647,0.0002665287,0.0001159299,0.0001058159,0.001082788],"genre_scores_gemma":[0.9974225,0.00003971416,0.0003711058,0.0002550045,0.0000726883,0.00008732683,0.0001542874,0.00001462727,0.001582786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1456549,"threshold_uncertainty_score":0.9462665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009007869330483746,"score_gpt":0.2283096913947444,"score_spread":0.2193018220642607,"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."}}