{"id":"W2964849433","doi":"10.1016/j.jag.2019.101914","title":"A dynamic classification scheme for mapping spectrally similar classes: Application to wetland classification","year":2019,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wetland; Set (abstract data type); Class (philosophy); Feature (linguistics); Land cover; Feature selection; Remote sensing; Field (mathematics); Geography; Selection (genetic algorithm); Data set; Data mining; Computer science; Pattern recognition (psychology); Artificial intelligence; Mathematics; Land use; Engineering; Ecology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0005391822,0.0001352204,0.0001584621,0.0001961947,0.0000834869,0.0001408548,0.000235013,0.00007865552,0.00008463881],"category_scores_gemma":[0.00007268366,0.0001343129,0.00005313068,0.0002175232,0.00002622288,0.0007292134,0.00004846312,0.0001131968,0.0001580458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001503776,"about_ca_system_score_gemma":0.00003462157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001092851,"about_ca_topic_score_gemma":0.00002893997,"domain_scores_codex":[0.9984583,0.00001028354,0.0006867332,0.000183772,0.0005023333,0.0001586286],"domain_scores_gemma":[0.9987827,0.00008625592,0.0006832374,0.0001384598,0.0002364478,0.0000729247],"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":[0.001043758,0.0001975832,0.06238272,0.0001559008,0.0001961038,0.000001091736,0.004503686,0.0324165,0.4498563,0.05663748,0.004460762,0.3881481],"study_design_scores_gemma":[0.001032477,0.00008621641,0.51792,0.00003540117,0.00001217559,0.000009645399,0.0006736719,0.3702924,0.0004140778,0.002346091,0.1069958,0.0001820514],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6299756,0.000005755586,0.3619574,0.002483731,0.000344552,0.0008172009,0.0000192514,0.00002631244,0.004370122],"genre_scores_gemma":[0.9275025,0.00004833251,0.07035055,0.001572493,0.00007703955,0.00004597052,0.0002182247,0.00001308336,0.0001718774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4555373,"threshold_uncertainty_score":0.5477122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01688336059276171,"score_gpt":0.2487192240405819,"score_spread":0.2318358634478202,"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."}}