{"id":"W2089455804","doi":"10.5589/m09-035","title":"Using SAR images to delineate ocean oil slicks with a texture-classifying neural network algorithm (TCNNA)","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Oil Spill Detection and Mitigation","field":"Environmental Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Oceanic and Atmospheric Administration; Consejo Nacional de Ciencia y Tecnología; National Aeronautics and Space Administration","keywords":"Synthetic aperture radar; Racing slick; Remote sensing; Artificial neural network; Computer science; Artificial intelligence; Satellite; Pattern recognition (psychology); Geography; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002802629,0.0001607951,0.0001875399,0.0001367677,0.0003583306,0.0001232057,0.000104542,0.00006324994,0.00004544816],"category_scores_gemma":[0.00004487586,0.0001425945,0.00006952706,0.0004450945,0.0000741219,0.0002410449,0.000009919217,0.0002890577,0.00001304324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000473544,"about_ca_system_score_gemma":0.0001254635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005803972,"about_ca_topic_score_gemma":0.01127321,"domain_scores_codex":[0.9987835,0.00005965092,0.0002790036,0.0001808673,0.0002371301,0.0004598374],"domain_scores_gemma":[0.9988222,0.00001253028,0.0001893707,0.0001280173,0.00006255909,0.0007853032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000103976,0.000001233157,0.0001839263,0.000001270163,0.000006916207,0.0003160521,0.0002065753,0.03844311,0.002209738,2.618256e-7,0.0008959576,0.9577246],"study_design_scores_gemma":[0.001026442,0.000620623,0.0113187,0.0006124476,0.0001153448,0.007837271,0.0005466784,0.9061311,0.004469543,0.0002439508,0.0662834,0.0007944403],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7846183,0.0001742779,0.2089022,0.002493169,0.0005886445,0.00008234316,0.000002918943,0.00002385022,0.003114357],"genre_scores_gemma":[0.6532212,0.000006756638,0.3438805,0.002237482,0.0004238302,1.709549e-9,8.333696e-7,0.00001942804,0.0002099791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9569301,"threshold_uncertainty_score":0.8773908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501311276695862,"score_gpt":0.2275444779054282,"score_spread":0.2125313651384696,"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."}}