{"id":"W3040971327","doi":"","title":"Delineation of Road Networks from Remote Sensor Data with Deep Learning","year":2019,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Computer science; Segmentation; Pipeline (software); Orthophoto; Deep learning; Artificial intelligence; Geospatial analysis; Artificial neural network; Task (project management); Data mining; Machine learning; Geography; Cartography; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002943324,0.0002879301,0.0004125334,0.0007205763,0.0002639882,0.00008487282,0.0007093764,0.0004885314,0.00003396285],"category_scores_gemma":[0.00004420599,0.0003092846,0.00007901279,0.0007983226,0.00006834739,0.0004548913,0.0000982795,0.00161743,0.00002293094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000385192,"about_ca_system_score_gemma":0.0002009198,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262821,"about_ca_topic_score_gemma":0.005652376,"domain_scores_codex":[0.9977865,0.0002463056,0.0002862294,0.0006059395,0.0006081135,0.0004668632],"domain_scores_gemma":[0.9983492,0.000192598,0.0002054943,0.0008790671,0.0002499799,0.0001236761],"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":[0.003283707,0.0001625491,0.03304347,0.001470659,0.002691143,0.001594843,0.001318269,0.7450516,0.07794667,0.0001348286,0.001635375,0.1316669],"study_design_scores_gemma":[0.0006723548,0.0002373057,0.03939988,0.0006119862,0.0002120538,0.00001465619,0.002454198,0.9351547,0.0108807,0.000008087911,0.009823124,0.0005309676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9618431,0.0005744949,0.01064791,0.00001194151,0.001058952,0.0004076552,0.00002359082,0.0004292056,0.02500316],"genre_scores_gemma":[0.9813997,0.0007285235,0.0002438843,5.885037e-7,0.0003866467,4.304991e-7,0.002327074,0.00009555719,0.01481766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1901032,"threshold_uncertainty_score":0.9999359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01928786402885591,"score_gpt":0.2587019855915616,"score_spread":0.2394141215627057,"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."}}