{"id":"W4221151155","doi":"10.1109/tgrs.2024.3357589","title":"Hyperspectral Pixel Unmixing With Latent Dirichlet Variational Autoencoder","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Pixel; Autoencoder; Pattern recognition (psychology); Dirichlet distribution; Artificial intelligence; Computer science; Remote sensing; Abundance estimation; Mixing (physics); Mathematics; Geography; Artificial neural network; Physics; Abundance (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140661,0.001357154,0.0009967468,0.0006584925,0.0003857511,0.0009605143,0.002047113,0.001380819,0.002210325],"category_scores_gemma":[0.002056284,0.001003164,0.001679094,0.0007484497,0.0009224162,0.001491664,0.001665734,0.003323101,0.001193063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088166,"about_ca_system_score_gemma":0.001236712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006880763,"about_ca_topic_score_gemma":0.01226516,"domain_scores_codex":[0.999352,0.0001785364,0.00002866628,0.0001996038,0.0001871144,0.00005397293],"domain_scores_gemma":[0.9995241,0.0002103666,0.00004393606,0.00009819485,0.00009932988,0.00002399324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001239998,0.00009176872,0.0006812896,0.0001498528,0.0002089337,0.00009191859,0.0001606633,0.737114,0.01180653,0.02128151,0.005818863,0.2224707],"study_design_scores_gemma":[0.000004212426,0.000005340965,0.0000492932,0.000004400503,0.000004307545,0.00001168132,0.00000421141,0.9933449,0.001562625,0.004044649,0.0009587585,0.000005715949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00297011,0.0001813886,0.9950024,0.0001113944,0.00003145968,0.00002899714,0.0001364977,0.0007835054,0.0007541901],"genre_scores_gemma":[0.1390391,0.0003528674,0.8502682,0.0003202858,0.0001164531,0.0002589604,0.001781284,0.0006255711,0.007237197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006880763,"threshold_uncertainty_score":0.01368141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01264203929887554,"score_gpt":0.2189277843140964,"score_spread":0.2062857450152209,"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."}}