{"id":"W4389128676","doi":"10.3390/fire6120455","title":"BoucaNet: A CNN-Transformer for Smoke Recognition on Remote Sensing Satellite Images","year":2023,"lang":"en","type":"article","venue":"Fire","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Smoke; Haze; Deep learning; Computer science; Fire detection; Artificial intelligence; Ignition system; Transformer; Environmental science; Satellite; Firefighting; Remote sensing; Engineering; Meteorology; Cartography; Geography; Waste management; Aerospace engineering; Architectural engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003491184,0.0016204,0.000500189,0.0009628095,0.0003051432,0.0005541848,0.001747839,0.0007209909,0.005434363],"category_scores_gemma":[0.0009019296,0.0004678428,0.0006731491,0.0005313187,0.0003035748,0.001028672,0.0007878206,0.0008878083,0.001925259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001020067,"about_ca_system_score_gemma":0.00110091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02478099,"about_ca_topic_score_gemma":0.04305284,"domain_scores_codex":[0.9998324,0.000013374,0.000007038533,0.00006287984,0.00004215667,0.0000421426],"domain_scores_gemma":[0.9998735,0.00002371917,0.00001390633,0.00002412875,0.00004783552,0.00001685237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005281345,0.0003524982,0.005703831,0.0004027787,0.0002774355,0.0002702537,0.00007188971,0.08580799,0.06866843,0.004732364,0.03219105,0.8009934],"study_design_scores_gemma":[0.00002709763,0.0001240603,0.001605195,0.00003378439,0.00005133099,0.0001630278,0.00002505856,0.9563736,0.03106771,0.002508063,0.007997985,0.00002309286],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1075701,0.002427781,0.8230541,0.0004358674,0.0007605884,0.0004920662,0.003059339,0.0467229,0.0154772],"genre_scores_gemma":[0.6645038,0.001077126,0.2993119,0.000841552,0.0001156207,0.0002909409,0.008546028,0.001005451,0.02430759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02478099,"threshold_uncertainty_score":0.04927349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03107516433778969,"score_gpt":0.2408779017424404,"score_spread":0.2098027374046507,"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."}}