{"id":"W3099257724","doi":"10.3389/fenvs.2020.579856","title":"Branching Algorithm to Identify Bottom Habitat in the Optically Complex Coastal Waters of Atlantic Canada Using Sentinel-2 Satellite Imagery","year":2020,"lang":"en","type":"article","venue":"Frontiers in Environmental Science","topic":"Marine and fisheries research","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bedford Institute of Oceanography; Fisheries and Oceans Canada","funders":"Fisheries and Oceans Canada","keywords":"Satellite imagery; Oceanography; Ocean color; Satellite; Remote sensing; Habitat; Environmental science; Algorithm; Geology; Ecology; Computer science; Biology; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000713692,0.0001784068,0.000240415,0.00006641652,0.0001677528,0.0000830554,0.001036911,0.00003315886,0.0002889269],"category_scores_gemma":[0.00005662317,0.0001480722,0.00004297688,0.0009400127,0.001180297,0.0004419746,0.0008827279,0.000288377,0.00001426408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006787297,"about_ca_system_score_gemma":0.00008473071,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.09065973,"about_ca_topic_score_gemma":0.01692993,"domain_scores_codex":[0.9969815,0.0001110678,0.0003938511,0.0005507457,0.001278526,0.0006842792],"domain_scores_gemma":[0.9993794,0.00004233707,0.00006671701,0.000262929,0.000002506087,0.0002461196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002212224,0.00004133708,0.9276227,0.000008496249,0.000002596427,0.00008162145,0.0009170766,0.0009171024,0.0628835,0.000001428492,0.0004903134,0.007011653],"study_design_scores_gemma":[0.0002638029,0.0000407611,0.9529884,0.000008866472,0.000004269764,0.00001044771,0.002418087,0.04162928,0.0006345017,0.00002083755,0.001765643,0.0002150787],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920959,0.000008573297,0.004151914,0.000903861,0.0001247764,0.0003557935,0.00001709824,0.000005503748,0.002336608],"genre_scores_gemma":[0.9768807,0.00001939057,0.02214458,0.0008895016,0.00002029962,0.000006941939,0.000008928112,0.00001168758,0.0000179483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07372981,"threshold_uncertainty_score":0.9447296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01569510452971602,"score_gpt":0.2428818870785463,"score_spread":0.2271867825488303,"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."}}