{"id":"W2898837206","doi":"10.4043/29130-ms","title":"Towards Automation of Satellite-Based Radar Imagery for Iceberg Surveillance - Machine Learning of Ship and Iceberg Discrimination","year":2018,"lang":"en","type":"article","venue":"OTC Arctic Technology Conference","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering","funders":"","keywords":"Iceberg; Synthetic aperture radar; Computer science; Remote sensing; Constant false alarm rate; Clutter; Automation; Satellite; Cloud computing; Radar; Real-time computing; Sea ice; Meteorology; Artificial intelligence; Geology; Engineering; Geography; Telecommunications","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":[0.0004390051,0.0001484204,0.0002835952,0.0002090169,0.0001426111,0.00001411803,0.0002044011,0.0001524267,0.0002430521],"category_scores_gemma":[0.0005315796,0.0001315153,0.00004162578,0.0002755228,0.000862331,0.0001383621,0.00002528244,0.000160545,0.00000645039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000821406,"about_ca_system_score_gemma":0.0001035564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007715205,"about_ca_topic_score_gemma":0.0009118833,"domain_scores_codex":[0.9989281,0.00006540834,0.0003307948,0.0002713337,0.0001631442,0.0002411901],"domain_scores_gemma":[0.9988881,0.0002825311,0.0003142159,0.0001990832,0.0002731483,0.00004289712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001203352,0.00002864589,0.7278032,0.0003150318,0.00002792283,0.0000013379,0.0003724184,0.00002335408,0.001329942,0.007069453,0.000004010742,0.2629043],"study_design_scores_gemma":[0.001009159,0.001155463,0.7681771,0.0002064582,0.00007271052,0.00002461215,0.0009514426,0.2023356,0.006855167,0.01806904,0.00078638,0.0003568961],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8979004,0.0002812418,0.09801839,0.001805656,0.0001896322,0.0003293519,0.00009781498,0.0001145409,0.001262992],"genre_scores_gemma":[0.9769391,0.0001418373,0.02263792,0.00003679015,0.00002317678,0.000003359642,0.0001298333,0.000005478358,0.00008246153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2625475,"threshold_uncertainty_score":0.5363038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01457418119733395,"score_gpt":0.2310032243867717,"score_spread":0.2164290431894378,"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."}}