{"id":"W4316036976","doi":"10.31223/x52d39","title":"Residual U-Net with Attention for Detecting Clouds in Satellite Imagery","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Canarie","keywords":"Computer science; Residual; Cloud computing; Segmentation; Satellite imagery; Jaccard index; Artificial intelligence; Variety (cybernetics); Benchmark (surveying); Deep learning; Unavailability; Satellite; Machine learning; Remote sensing; Pattern recognition (psychology); Cartography; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006389594,0.001222532,0.0005620369,0.0006458037,0.0003406126,0.0006681701,0.001383139,0.0009745163,0.002000712],"category_scores_gemma":[0.00122603,0.0003231166,0.0005695859,0.0008123589,0.0005302482,0.001376585,0.0008416765,0.001261179,0.0009632596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001086613,"about_ca_system_score_gemma":0.0008245968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0177523,"about_ca_topic_score_gemma":0.02611863,"domain_scores_codex":[0.9997984,0.00003431952,0.000008087672,0.00007656958,0.00003704376,0.00004556773],"domain_scores_gemma":[0.9997533,0.00008603989,0.00003164488,0.00004637239,0.00005917339,0.00002339752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009242032,0.0004492838,0.005922173,0.0002154181,0.0001697286,0.0002337871,0.0001048589,0.4770983,0.01359933,0.006609696,0.02513141,0.4695418],"study_design_scores_gemma":[0.000007525523,0.00003619209,0.0004366585,0.000009222662,0.00001245749,0.0000168955,0.00001076023,0.9930676,0.003250411,0.002359795,0.0007871781,0.00000528053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3451372,0.003819716,0.6151916,0.001444529,0.0004260569,0.0002447526,0.00234731,0.01679833,0.01459061],"genre_scores_gemma":[0.8659826,0.0005974555,0.1165622,0.000631777,0.0001244066,0.0001213742,0.004992072,0.0002803731,0.01070773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0177523,"threshold_uncertainty_score":0.03529793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04236751824807769,"score_gpt":0.2634735318092069,"score_spread":0.2211060135611292,"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."}}