{"id":"W4389939988","doi":"10.1029/2023gc011250","title":"Automated Seafloor Massive Sulfide Detection Through Integrated Image Segmentation and Geophysical Data Analysis: Revisiting the TAG Hydrothermal Field","year":2023,"lang":"en","type":"article","venue":"Geochemistry Geophysics Geosystems","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Geology; Workflow; Seafloor spreading; Coring; Mineral exploration; Geospatial analysis; Bathymetry; Volcanogenic massive sulfide ore deposit; Segmentation; Geophysics; Computer science; Remote sensing; Artificial intelligence; Seismology; Oceanography; Hydrothermal circulation; Drilling; Database","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006987583,0.0003769381,0.000452616,0.00006343829,0.0005442388,0.0004678592,0.001442382,0.000185998,0.00002125328],"category_scores_gemma":[0.0002904975,0.0003068809,0.0001482938,0.002454217,0.0001031759,0.0007658039,0.001049528,0.0004256825,0.00008705438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004707646,"about_ca_system_score_gemma":0.00007885381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007844025,"about_ca_topic_score_gemma":0.00001517201,"domain_scores_codex":[0.9971036,0.000186972,0.0005274903,0.001106398,0.000465673,0.000609875],"domain_scores_gemma":[0.9968884,0.0004592984,0.0004011959,0.001878888,0.0002664148,0.0001058157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006012724,0.0001054917,0.001274472,0.001265439,0.001997461,0.0002354118,0.002668379,0.005338766,0.9442128,0.001187047,0.004291945,0.03736269],"study_design_scores_gemma":[0.0003329186,0.00002671583,0.001064788,0.00009234731,0.0002213993,0.00003105061,0.001286741,0.8616636,0.1317374,0.001751333,0.001370237,0.0004214986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7790943,0.0003059188,0.1985845,0.009096552,0.000640439,0.001183083,0.0003182123,0.004138496,0.006638474],"genre_scores_gemma":[0.9966488,0.00002304852,0.001041282,0.0001362983,0.0005537804,0.00008708585,0.0007788769,0.00001115331,0.0007196736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8563249,"threshold_uncertainty_score":0.9999383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164571804639377,"score_gpt":0.2597148627639739,"score_spread":0.2432576823000362,"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."}}