{"id":"W3210709473","doi":"10.1109/jstars.2021.3123163","title":"Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Oil Spill Detection and Mitigation","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; Government of Newfoundland and Labrador","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Computer science; Kernel (algebra); Remote sensing; Convolutional neural network; Deep learning; Scale (ratio); Artificial intelligence; Convolution (computer science); Satellite imagery; Satellite; Constant false alarm rate; Key (lock); Pattern recognition (psychology); Artificial neural network; Environmental science; Algorithm; Geology; Cartography; Mathematics; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0004333806,0.0001555558,0.0002254572,0.0001319526,0.0002741015,0.00005142139,0.00003532824,0.0001500783,0.00001062702],"category_scores_gemma":[0.0003455562,0.0001526186,0.00006644156,0.0005152187,0.00008629074,0.00008685837,0.00001929452,0.0003930482,0.000002924433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001488648,"about_ca_system_score_gemma":0.00008249479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007210048,"about_ca_topic_score_gemma":0.0007674839,"domain_scores_codex":[0.9985411,0.00006356042,0.0005026223,0.0002688788,0.0003799605,0.0002439418],"domain_scores_gemma":[0.9990931,0.0002238843,0.0002178557,0.000134919,0.0002235341,0.0001066956],"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":[0.00008087092,0.0000177721,0.00002818963,0.0000131526,0.000007653126,0.00002258521,0.00005256652,0.01085956,0.4060856,0.00000897017,0.00002461868,0.5827985],"study_design_scores_gemma":[0.001497639,0.0001056128,0.02109827,0.0001532267,0.00003198902,0.000152166,0.00007176654,0.6899839,0.2837233,0.0003944479,0.002577648,0.0002100883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8522486,0.00001593879,0.1454729,0.0008703386,0.0004186305,0.00008446573,0.000002775526,0.0000220554,0.0008643421],"genre_scores_gemma":[0.5271121,0.00004032668,0.4718386,0.0004640358,0.000278632,4.502456e-8,0.000007041323,0.00001913115,0.0002401197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6791243,"threshold_uncertainty_score":0.6223604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01860869280984786,"score_gpt":0.2324006732630371,"score_spread":0.2137919804531892,"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."}}