{"id":"W2109377525","doi":"10.1007/s10661-005-3499-y","title":"Using Aerial Video to Train the Supervised Classification of Landsat Tm Imagery for Coral Reef Habitats Mapping","year":2005,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Coral and Marine Ecosystems Studies","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trent University","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Bathymetry; Coral reef; Thematic map; Thematic Mapper; Remote sensing; Reef; Habitat; Satellite imagery; Aerial photography; Geography; Cartography; Environmental science; Ecology; Geology; Oceanography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002578326,0.0001433975,0.0001693894,0.0000233786,0.0002724128,0.00003036064,0.0001101632,0.00003049378,0.00004270438],"category_scores_gemma":[0.000007861268,0.0001098058,0.00005608967,0.00005634819,0.00008444725,0.0001462157,0.000230128,0.00007359937,0.000008990842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603997,"about_ca_system_score_gemma":0.000005171503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009161151,"about_ca_topic_score_gemma":0.0000120853,"domain_scores_codex":[0.9989986,0.00003908581,0.000256207,0.000267979,0.0002159846,0.0002221537],"domain_scores_gemma":[0.9996127,0.00007217607,0.00008589527,0.0001561925,0.000002120124,0.00007085044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004798001,0.0001223361,0.385172,0.00002166938,0.00002669666,9.336717e-7,0.0008592335,0.0002387652,0.536175,0.00001800497,0.0002652438,0.07705215],"study_design_scores_gemma":[0.0005362328,0.0001160844,0.9802223,0.00003642419,0.00002511496,0.000004592188,0.001939787,0.003226532,0.004728398,0.00004119676,0.008946963,0.0001763101],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968345,0.00006007455,0.001242242,0.0006910408,0.0003154232,0.0004664535,0.00002194366,0.00001401888,0.0003543558],"genre_scores_gemma":[0.9862431,0.00003277259,0.01302889,0.00002434301,0.0003712183,0.0000904077,0.000006337255,0.0000129373,0.0001899917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5950503,"threshold_uncertainty_score":0.447775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05479452777552107,"score_gpt":0.2976829491765106,"score_spread":0.2428884214009895,"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."}}