{"id":"W2112315008","doi":"10.1111/j.2006.0906-7590.04596.x","title":"Novel methods improve prediction of species’ distributions from occurrence data","year":2006,"lang":"en","type":"article","venue":"Ecography","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":9099,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Herbarium; Computer science; Context (archaeology); Predictive modelling; Species distribution; Environmental niche modelling; Data set; Environmental data; Ecology; Machine learning; Data mining; Data science; Artificial intelligence; Geography; Biology; Habitat","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01051903,0.001423673,0.001591402,0.003300963,0.000563657,0.001835183,0.002589969,0.001944431,0.001897644],"category_scores_gemma":[0.03503767,0.0007269962,0.001733819,0.002363299,0.0007681499,0.004820199,0.002206705,0.002276716,0.0009800484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001100669,"about_ca_system_score_gemma":0.001084628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00508865,"about_ca_topic_score_gemma":0.007981343,"domain_scores_codex":[0.9959953,0.001655761,0.0003339879,0.001159067,0.0006925854,0.0001633783],"domain_scores_gemma":[0.9573762,0.03358374,0.003155839,0.002936321,0.002595831,0.0003519604],"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":[0.0004941317,0.0005868457,0.07241534,0.0004822961,0.001359456,0.0001483337,0.0003550957,0.4604771,0.004434879,0.007019449,0.004812825,0.4474141],"study_design_scores_gemma":[0.00004781814,0.00007358014,0.007964174,0.0000262263,0.00006687248,0.0001101438,0.00003028369,0.9835096,0.000851053,0.005839667,0.001445396,0.00003521728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1409356,0.001592911,0.8511618,0.0007763189,0.0002504126,0.0001130083,0.0009205714,0.002220417,0.002028954],"genre_scores_gemma":[0.5109943,0.0006184956,0.4838222,0.0002973852,0.0003939842,0.0001884282,0.002016075,0.0002999985,0.001369179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01051903,"threshold_uncertainty_score":0.05563062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05803130636803126,"score_gpt":0.2955582420672953,"score_spread":0.237526935699264,"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."}}