{"id":"W4387801729","doi":"10.1109/igarss52108.2023.10282323","title":"Semantic Segmentation of Burned Areas in Sentinel-2 Satellite Images Using Deep Learning Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Deep learning; Computer science; Artificial intelligence; Task (project management); Satellite imagery; Machine learning; Image segmentation; Satellite; Remote sensing; Geography; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005137863,0.001017225,0.0004268312,0.001641693,0.0002811331,0.00081535,0.0006648046,0.0006307494,0.001080353],"category_scores_gemma":[0.0009326804,0.0002608451,0.00105186,0.001119047,0.0004469125,0.00108328,0.000675849,0.0007344073,0.000485856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009024888,"about_ca_system_score_gemma":0.0009012226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02353699,"about_ca_topic_score_gemma":0.04170785,"domain_scores_codex":[0.9997157,0.00003803386,0.00001950071,0.0001006824,0.00005839436,0.00006755962],"domain_scores_gemma":[0.9997739,0.00005894509,0.00003889417,0.00004001897,0.00006779933,0.00002042028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005037181,0.0003859209,0.03112318,0.0002546661,0.0002806678,0.000262222,0.0002879827,0.6435441,0.01937269,0.00303894,0.01510143,0.2858445],"study_design_scores_gemma":[0.00001189989,0.00003084523,0.00583151,0.00002747264,0.0000263229,0.00004024565,0.0001153823,0.9841694,0.005571255,0.002448455,0.001712749,0.00001452314],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7265123,0.001517678,0.2451767,0.0006903333,0.0002937346,0.0001874088,0.009945959,0.007783463,0.007892407],"genre_scores_gemma":[0.8795042,0.0003937054,0.097765,0.0002594846,0.00005066013,0.00006773329,0.01964145,0.0002422127,0.002075661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02353699,"threshold_uncertainty_score":0.04679996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02065260271529714,"score_gpt":0.247705719859925,"score_spread":0.2270531171446279,"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."}}