{"id":"W2156220628","doi":"10.1016/j.rse.2007.02.019","title":"Integration of spatial–spectral information for the improved extraction of endmembers","year":2007,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":243,"is_retracted":false,"has_abstract":false,"ca_institutions":"Geological Survey of Canada; University of Alberta","funders":"","keywords":"Endmember; Hyperspectral imaging; Pattern recognition (psychology); Contrast (vision); Pixel; Artificial intelligence; Spectral signature; Projection (relational algebra); Mathematics; Computer science; Basis (linear algebra); Singular value decomposition; Set (abstract data type); Remote sensing; Computer vision; Algorithm; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0004189789,0.0001022773,0.0001463469,0.00009621264,0.00002754723,0.000006127448,0.00004848079,0.00007202665,0.000003212172],"category_scores_gemma":[0.00008072704,0.00008884822,0.00007926879,0.00006061689,0.00008018417,0.0001521036,0.000007735408,0.00008502234,0.000001551336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453294,"about_ca_system_score_gemma":0.000008421063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001918245,"about_ca_topic_score_gemma":0.00003095367,"domain_scores_codex":[0.9990991,0.00001283734,0.0005157801,0.00007397262,0.0001728605,0.0001253882],"domain_scores_gemma":[0.999212,0.0001804339,0.0002859961,0.0002579986,0.00004226185,0.0000212557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002639659,0.000004896859,0.000001747938,0.00004042702,0.00001653208,5.74314e-8,0.0002654865,0.01346047,0.6389139,0.000009834252,0.00001063504,0.3472496],"study_design_scores_gemma":[0.0001417521,0.00003261161,0.004505669,0.00002884701,0.00002692295,0.000003062573,0.0001595281,0.4846196,0.5099803,0.00004035789,0.0004152136,0.00004611034],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1851016,0.00003184676,0.8138685,0.0000426126,0.0001973717,0.0003144558,0.000003653742,0.00002276142,0.000417264],"genre_scores_gemma":[0.9152045,0.00006677364,0.08464321,0.00000450758,0.00003632849,5.919834e-8,0.00001858684,0.00001425643,0.00001182635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7301028,"threshold_uncertainty_score":0.3623126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114947609014279,"score_gpt":0.2250849863342493,"score_spread":0.2135902254328214,"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."}}