{"id":"W4381250385","doi":"10.1109/tgrs.2023.3287498","title":"Tokenized Time-Series in Satellite Image Segmentation With Transformer Network for Active Fire Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Vetenskapsrådet; Svenska Forskningsrådet Formas","keywords":"Pixel; Visible Infrared Imaging Radiometer Suite; Computer science; Remote sensing; Convolutional neural network; Artificial intelligence; Deep learning; Image resolution; Fire detection; Thresholding; Multispectral image; Segmentation; Computer vision; Satellite; Image (mathematics); Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000335514,0.000153597,0.000154702,0.00008682955,0.0004436611,0.00005673369,0.0000524385,0.00006595757,0.0000148347],"category_scores_gemma":[0.000004453884,0.0001295424,0.00004204216,0.0009234511,0.0001911464,0.000598937,0.000001025885,0.0001228247,0.00006956008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283503,"about_ca_system_score_gemma":0.00001176348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008823785,"about_ca_topic_score_gemma":0.003146818,"domain_scores_codex":[0.9988021,0.00006076397,0.0001716102,0.0003782489,0.0002167305,0.0003705116],"domain_scores_gemma":[0.9996314,0.0001238261,0.00005201876,0.0001148043,0.00001139918,0.00006653624],"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":[0.0002326772,0.000009980058,0.000004923061,0.00001619672,0.00000525514,0.000006784751,0.0007405021,0.004155224,0.1245936,7.044909e-8,0.000006371277,0.8702284],"study_design_scores_gemma":[0.001051687,0.0005380805,0.004383703,0.0001664488,0.00003249054,0.00008069474,0.000554005,0.7416064,0.2507183,0.00009789786,0.0004141967,0.0003561684],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6131922,0.000004169131,0.3856031,0.0001557393,0.000217823,0.000590474,0.000008104957,0.00008567119,0.0001427505],"genre_scores_gemma":[0.9651802,0.0001295017,0.03374996,0.00007602371,0.00003321731,0.000004545598,0.000004540738,0.00002700518,0.0007950137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8698722,"threshold_uncertainty_score":0.5282584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005976293694055281,"score_gpt":0.2124568059179966,"score_spread":0.2064805122239414,"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."}}