{"id":"W4408174455","doi":"10.14358/pers.24-00100r2","title":"A Comparative Study of Deep Learning Methods for Automated Road Network Extraction from High-Spatial-Resolution Remotely Sensed Imagery","year":2025,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Calgary; University of Waterloo","funders":"","keywords":"Computer science; Deep learning; Remote sensing; Artificial intelligence; High resolution; Aerial imagery; Extraction (chemistry); Cartography; Computer vision; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005396289,0.002703947,0.001044914,0.004368569,0.0005741012,0.00144269,0.001793957,0.001856959,0.001536897],"category_scores_gemma":[0.009292024,0.0005572323,0.00143801,0.00222922,0.0005632521,0.004076208,0.001325016,0.002016988,0.001143619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001563482,"about_ca_system_score_gemma":0.00142343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01572834,"about_ca_topic_score_gemma":0.02129037,"domain_scores_codex":[0.9968334,0.0007343215,0.0002833497,0.0008022264,0.001100982,0.0002458425],"domain_scores_gemma":[0.9960699,0.001789867,0.0002044093,0.000599377,0.001177584,0.0001589073],"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":[0.001026562,0.0006916418,0.01545157,0.001112749,0.0008551137,0.0002005767,0.0001517317,0.1213051,0.005806746,0.002925401,0.01924742,0.8312253],"study_design_scores_gemma":[0.00008561503,0.0006317467,0.009157182,0.0002285799,0.0002487455,0.0002269483,0.0002216449,0.9627482,0.01425312,0.002003729,0.01011455,0.00007986121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5984039,0.06386267,0.2824487,0.003590462,0.00179755,0.0007493367,0.00845518,0.01315907,0.02753304],"genre_scores_gemma":[0.738713,0.01567004,0.2066466,0.0007611318,0.0003274312,0.0002890419,0.02597255,0.0005440456,0.01107613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01572834,"threshold_uncertainty_score":0.03127354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01546688194457353,"score_gpt":0.3045463281253198,"score_spread":0.2890794461807463,"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."}}