{"id":"W2971438317","doi":"10.1016/j.jag.2019.101957","title":"Incorporating band selection in the spatial selection of spectral endmembers","year":2019,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; University of Alberta","keywords":"Endmember; Hyperspectral imaging; Computer science; Selection (genetic algorithm); Pattern recognition (psychology); Artificial intelligence; Feature selection; Spectral bands; Set (abstract data type); Remote sensing; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001105733,0.0006202018,0.0004084798,0.0008174676,0.0004269384,0.0007692204,0.0004002004,0.0005007068,0.001004377],"category_scores_gemma":[0.001788414,0.0002560474,0.0005812038,0.0008062741,0.0002569589,0.0007814316,0.0005325411,0.0004188785,0.0007079671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001391463,"about_ca_system_score_gemma":0.000714433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003318707,"about_ca_topic_score_gemma":0.008765107,"domain_scores_codex":[0.9996657,0.0001117088,0.00001959199,0.00005541978,0.00009738486,0.00005027948],"domain_scores_gemma":[0.9994072,0.0001896042,0.00003965332,0.00007882697,0.0002597647,0.00002496252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007238101,0.0004278874,0.01163414,0.0001839659,0.0002415319,0.0001130773,0.0002221128,0.1333412,0.1721427,0.003015994,0.003291807,0.6746618],"study_design_scores_gemma":[0.0000326595,0.00009838278,0.01197347,0.00002806739,0.0001765317,0.0001118273,0.0000669858,0.9366058,0.04458829,0.002538478,0.003739906,0.00003969553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.117543,0.0003945208,0.8789722,0.0001351115,0.00009306444,0.00005727123,0.0001926674,0.0008753311,0.001736721],"genre_scores_gemma":[0.459517,0.0004483649,0.5359029,0.0001494766,0.00009416596,0.00008353111,0.0006096538,0.0002064675,0.002988428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003318707,"threshold_uncertainty_score":0.006598771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00899900703918599,"score_gpt":0.2038885637019597,"score_spread":0.1948895566627737,"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."}}