{"id":"W3020665929","doi":"10.1016/j.pocean.2020.102338","title":"Improving the predictive capability of benthic species distribution models by incorporating oceanographic data – Towards holistic ecological modelling of a submarine canyon","year":2020,"lang":"en","type":"article","venue":"Progress In Oceanography","topic":"Coral and Marine Ecosystems Studies","field":"Environmental Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Horizon 2020; Natural Environment Research Council; Sight Research UK","keywords":"Submarine canyon; Benthic zone; Canyon; Megafauna; Environmental science; Oceanography; Species richness; Biodiversity; Environmental niche modelling; Ecology; Species distribution; Predictive modelling; Habitat; Geography; Geology; Cartography; Computer science; Ecological niche; Biology; Machine learning","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":[0.0007069929,0.0005709469,0.0004334036,0.0005035621,0.0001931281,0.0008304699,0.0004860872,0.0004877804,0.0004828247],"category_scores_gemma":[0.001461767,0.000321405,0.0007269408,0.0003887353,0.0001802618,0.0006493444,0.0005734425,0.0007067938,0.0001342724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002506968,"about_ca_system_score_gemma":0.0005516983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0242716,"about_ca_topic_score_gemma":0.02075276,"domain_scores_codex":[0.9999017,0.00002855083,0.00000690888,0.00003264702,0.00001549792,0.00001468962],"domain_scores_gemma":[0.9996179,0.0002291183,0.00004263075,0.00003373808,0.00005278065,0.00002377382],"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":[0.0000233858,0.0000226934,0.01120075,0.00002006058,0.00007095581,0.00003088452,0.00003718671,0.9738356,0.001213141,0.00028215,0.0001087899,0.01315444],"study_design_scores_gemma":[0.000001606797,0.000007221893,0.002762696,0.000004621755,0.000007897641,0.000004028807,0.00001005195,0.9966419,0.000133526,0.000340507,0.00008259661,0.000003298644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7887211,0.0004390682,0.207984,0.0002483204,0.00003063164,0.00003120218,0.0006021067,0.0005518543,0.00139164],"genre_scores_gemma":[0.97651,0.0001731399,0.02241366,0.00002998603,0.00001258811,0.00002688111,0.0004870997,0.00002849358,0.000318077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0242716,"threshold_uncertainty_score":0.04826069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06392485341325808,"score_gpt":0.2451838935498573,"score_spread":0.1812590401365992,"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."}}