{"id":"W1988627994","doi":"10.1117/12.799232","title":"Improved iterative error analysis for endmember extraction from hyperspectral imagery","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Pattern recognition (psychology); Computer science; Abundance estimation; Artificial intelligence; Constraint (computer-aided design); Image (mathematics); Feature extraction; Set (abstract data type); Algorithm; Mathematics; Abundance (ecology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003305437,0.0003901315,0.0005537843,0.0002148806,0.0001228152,0.0001191226,0.0005282453,0.0002376796,0.00001596806],"category_scores_gemma":[0.0004922845,0.0003603239,0.001071208,0.000567102,0.0002143845,0.0008516571,0.00005124265,0.000340898,0.00000187262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003301318,"about_ca_system_score_gemma":0.00002852844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001773054,"about_ca_topic_score_gemma":5.182151e-7,"domain_scores_codex":[0.9978505,2.168497e-8,0.000766024,0.0004690051,0.0004875927,0.0004268356],"domain_scores_gemma":[0.9975806,0.0002669665,0.000320538,0.00009324522,0.001614713,0.0001239522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009677253,0.00008263068,0.0003155394,0.0001720429,0.001801317,1.680106e-7,0.0004805346,0.001931829,0.9805996,0.01199542,0.002309745,0.0002143566],"study_design_scores_gemma":[0.000828128,0.0001105439,0.003541662,0.00007412562,0.0006010906,0.0000144162,0.0007843972,0.5680074,0.4243362,0.0003474738,0.0009511084,0.0004034834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931085,0.0001080959,0.003524865,0.0007203576,0.0003685071,0.0006513585,0.000145322,0.0002359986,0.001137031],"genre_scores_gemma":[0.7240546,0.00008477106,0.2747725,0.0000367729,0.0005491981,0.0001290829,0.00005772612,0.0000933496,0.0002219873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5660756,"threshold_uncertainty_score":0.9998848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01855396176670796,"score_gpt":0.2434374902112321,"score_spread":0.2248835284445241,"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."}}