{"id":"W3199331972","doi":"10.1080/10106049.2021.1983034","title":"Extracting built-up land area of airports in China using Sentinel-2 imagery through deep learning","year":2021,"lang":"en","type":"article","venue":"Geocarto International","topic":"Impact of Light on Environment and Health","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"China; Beijing; Built-up area; Geography; Land use; Deep learning; Remote sensing; Benchmark (surveying); Cartography; Transport engineering; Environmental science; Physical geography; Civil engineering; Computer science; Engineering; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002961823,0.0001100618,0.0001473614,0.00004117222,0.00006644895,0.00002491661,0.0001226246,0.00005107432,0.005024399],"category_scores_gemma":[0.0001189147,0.0001148827,0.00005481051,0.0001349277,0.00006191181,0.0004167573,0.0001803613,0.0002088669,0.00005421755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001846914,"about_ca_system_score_gemma":0.00002358074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000746674,"about_ca_topic_score_gemma":0.0001968027,"domain_scores_codex":[0.9987226,0.00004268508,0.0003090534,0.0002408734,0.0004048047,0.0002799491],"domain_scores_gemma":[0.9995856,0.00004605173,0.000180759,0.0001244596,0.00001050897,0.00005260136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001238905,0.00008015564,0.9804516,0.000006420147,0.000010097,0.0000549692,0.0007981333,0.005081555,0.01216471,0.00002040215,0.00004326904,0.001276323],"study_design_scores_gemma":[0.0003780995,0.00001052268,0.9841812,0.00003995869,0.000007012158,0.00006679069,0.0001893259,0.007238369,0.004051914,0.0003267837,0.003383571,0.0001264622],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9767346,0.00006836104,0.001126125,0.0004333922,0.00032157,0.00005119321,0.000002404316,0.00001360428,0.0212488],"genre_scores_gemma":[0.9973238,0.00005535999,0.001358232,0.0001212957,0.00008515463,0.00000212194,0.00003488146,0.00001203098,0.001007112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02058926,"threshold_uncertainty_score":0.9958851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337643694387657,"score_gpt":0.2862263382586302,"score_spread":0.2628499013147536,"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."}}