{"id":"W3154253854","doi":"10.1109/ieeeconf38699.2020.9389229","title":"Sea Ice Image Semantic Segmentation Using Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"Global Oceans 2020: Singapore – U.S. Gulf Coast","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Canadian Space Agency; Memorial University of Newfoundland","keywords":"Computer science; Segmentation; Artificial intelligence; Image segmentation; Pixel; Deep learning; Artificial neural network; Remote sensing; Process (computing); Computer vision; Pattern recognition (psychology); Geology","routes":{"ca_aff":true,"ca_fund":true,"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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001897453,0.0003580351,0.0003473924,0.00002667579,0.0004601584,0.000222841,0.0003565893,0.0001295702,0.001040927],"category_scores_gemma":[0.0000704948,0.000338328,0.0001569933,0.0007122845,0.0002004108,0.0005519202,0.00007157848,0.0003264299,0.0001185093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000428666,"about_ca_system_score_gemma":0.00008135062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001420535,"about_ca_topic_score_gemma":0.001322984,"domain_scores_codex":[0.9976571,0.0001322927,0.0004559643,0.0005585902,0.0004925514,0.000703468],"domain_scores_gemma":[0.9989538,0.00008257036,0.0002149407,0.0002114229,0.0001002572,0.0004370408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001769607,0.00003445112,0.681377,0.00007345789,0.00007548947,0.000414007,0.0005295356,0.2661411,0.00004891316,0.00004108896,0.002022918,0.04906509],"study_design_scores_gemma":[0.0004667657,0.0001327483,0.0493064,0.00002447114,0.0001189872,0.0002067641,0.001143259,0.9476203,0.000003870487,0.0001387764,0.0004564793,0.0003812118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8170928,0.0003702673,0.1756462,0.002593828,0.001071935,0.0003899745,0.0004453083,0.0002235105,0.002166227],"genre_scores_gemma":[0.9882539,0.00005383352,0.00674855,0.003337268,0.0006918282,3.429442e-7,0.0008867575,0.00001364891,0.00001390621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6814792,"threshold_uncertainty_score":0.9999069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01257362404175737,"score_gpt":0.2252657431989062,"score_spread":0.2126921191571489,"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."}}