{"id":"W4416727148","doi":"10.1109/igarss55030.2025.11242665","title":"Enhancing Crop Field Segmentation with Super-Resolved Sentinel-2 Imagery: A Deep Learning Approach Leveraging Multitemporal Edge Detection","year":2025,"lang":"","type":"article","venue":"","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"GDG Environnement; Institut National de la Recherche Scientifique","funders":"European Space Agency","keywords":"Deep learning; Segmentation; Field (mathematics); Image segmentation; Pattern recognition (psychology); Enhanced Data Rates for GSM Evolution; Image resolution; Pixel","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004949211,0.0005996278,0.0003065884,0.0007401917,0.0001485685,0.000584498,0.0006609988,0.0005769853,0.0008203748],"category_scores_gemma":[0.0007473187,0.0002958319,0.0004770274,0.0005088125,0.0003146545,0.001022284,0.000681793,0.0006498122,0.000469165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003506588,"about_ca_system_score_gemma":0.0004158526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003696195,"about_ca_topic_score_gemma":0.01079188,"domain_scores_codex":[0.9998398,0.00002622407,0.000004666293,0.00005196531,0.00004629704,0.00003105007],"domain_scores_gemma":[0.9998119,0.00005904467,0.00002366778,0.00003993029,0.00005101039,0.00001439489],"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":[0.0002733141,0.0002133198,0.009065601,0.0001504117,0.000167284,0.0002858906,0.0001936011,0.582972,0.1130605,0.003961558,0.005329239,0.2843273],"study_design_scores_gemma":[0.000005351167,0.00001829039,0.001731338,0.000006672928,0.0000131041,0.00005185804,0.00002284252,0.9861795,0.008778876,0.001819037,0.001362645,0.00001035975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1965418,0.0006888023,0.7929674,0.0006267724,0.00009770272,0.00005951285,0.0007875865,0.003077334,0.005152964],"genre_scores_gemma":[0.6361662,0.0004262197,0.3578264,0.0004183446,0.0000474047,0.00003705169,0.001864877,0.0002940769,0.002919359],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003696195,"threshold_uncertainty_score":0.007349372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007250156718278341,"score_gpt":0.2159081013090874,"score_spread":0.2086579445908091,"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."}}