{"id":"W3198844410","doi":"10.1080/07038992.2021.1956277","title":"Special Issue on Large-Scale Deep Learning for Sensor-Driven Mapping","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia; University of Calgary; University of Waterloo","funders":"","keywords":"Geospatial analysis; Remote sensing; Deep learning; Scale (ratio); Synthetic aperture radar; Geography; Data science; Computer science; Cartography; Radar imaging; Radar; Artificial intelligence; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001658745,0.0001229286,0.0002091696,0.0002429811,0.0002229846,0.00008237455,0.00005023589,0.0001113702,0.00006074641],"category_scores_gemma":[0.0001394909,0.0001368228,0.000121938,0.0001741586,0.00001371688,0.00009637588,0.000003497951,0.0004197553,0.00001775113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002611609,"about_ca_system_score_gemma":0.000150517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007784546,"about_ca_topic_score_gemma":0.003070368,"domain_scores_codex":[0.9991323,0.00003180087,0.0002607628,0.0001049031,0.0001095875,0.0003606387],"domain_scores_gemma":[0.9993151,0.0000546714,0.00009242915,0.00008484683,0.0001765449,0.0002764321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007565622,0.00000249697,0.0000537763,0.00005631968,0.00007539831,0.001033282,0.001651341,0.1070832,0.006025253,0.000006544431,0.006720376,0.8772845],"study_design_scores_gemma":[0.0002711899,0.00002548726,0.0002201791,0.000269563,0.00002121902,0.0009355657,0.001127946,0.3386483,0.003643365,0.00002825742,0.6546686,0.0001402986],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4323724,0.0005706532,0.5312111,0.0008660805,0.01092058,0.0001713658,0.00001028297,0.0001637105,0.02371387],"genre_scores_gemma":[0.581896,0.0001254182,0.3833428,0.0003203501,0.03286145,3.261197e-8,0.00002141394,0.0001625672,0.00126995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8771442,"threshold_uncertainty_score":0.5579473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01047827577898319,"score_gpt":0.2153828497634862,"score_spread":0.204904573984503,"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."}}