{"id":"W3040419708","doi":"10.71781/13167","title":"Identification of urban surface materials using high-resolution hyperspectral aerial imagery","year":2019,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Identification (biology); Aerial imagery; High resolution; Geography; Artificial intelligence; Cartography; Geology; Computer vision; Computer science; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002606356,0.0007030991,0.0002793345,0.002656478,0.0003239935,0.001158029,0.0003986998,0.0004717553,0.001716986],"category_scores_gemma":[0.0003049105,0.000266281,0.0005237994,0.001232298,0.0003204513,0.0005681062,0.0004003192,0.0002863852,0.001080901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006172842,"about_ca_system_score_gemma":0.000645005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02501776,"about_ca_topic_score_gemma":0.0678062,"domain_scores_codex":[0.999752,0.00001473714,0.000006500197,0.00005332604,0.0001270824,0.0000463775],"domain_scores_gemma":[0.9998345,0.000026406,0.00002052177,0.0000216562,0.00008686222,0.00001001487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002739629,0.0001826851,0.04873495,0.0007834216,0.0001794891,0.0006470718,0.0008399719,0.03465326,0.5767928,0.001546323,0.002977822,0.3323884],"study_design_scores_gemma":[0.00003605235,0.0001985048,0.3496653,0.0001375934,0.0001889159,0.0008496464,0.002200605,0.2146265,0.3973262,0.001529648,0.0330938,0.0001471673],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.800052,0.001187811,0.1763533,0.0002103141,0.00003860123,0.000283438,0.002938246,0.002754809,0.01618141],"genre_scores_gemma":[0.8311248,0.001066188,0.1526369,0.00009579076,0.00001886275,0.0001124844,0.003674225,0.0002513849,0.0110193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02501776,"threshold_uncertainty_score":0.04974431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006539727518120906,"score_gpt":0.1764281636414659,"score_spread":0.1698884361233449,"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."}}