{"id":"W4387802020","doi":"10.1109/igarss52108.2023.10282175","title":"An Iterative Method for Hyperspectral Pixel Unmixing Leveraging Latent Dirichlet Variational Autoencoder","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Pattern recognition (psychology); Autoencoder; Artificial intelligence; Computer science; Benchmark (surveying); Abundance estimation; Ground truth; Mathematics; Abundance (ecology); Deep learning; Geography; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001242818,0.0008537588,0.0007329136,0.0005834837,0.0003326465,0.0006062433,0.001552864,0.001141425,0.001780564],"category_scores_gemma":[0.001761422,0.0007245941,0.001142604,0.0005407641,0.0006439344,0.001052088,0.001359857,0.00175955,0.0008018288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008017814,"about_ca_system_score_gemma":0.001298886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006758574,"about_ca_topic_score_gemma":0.01039608,"domain_scores_codex":[0.9993923,0.0001409523,0.00002820421,0.0001636849,0.0002225931,0.00005232634],"domain_scores_gemma":[0.9995151,0.0002198716,0.00004726663,0.00005531375,0.0001373383,0.00002502245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009633467,0.00007802386,0.0006575299,0.0001297929,0.0001501905,0.00007174732,0.0001765581,0.6610872,0.03153017,0.01341732,0.002407091,0.290198],"study_design_scores_gemma":[0.000002970395,0.000006406869,0.00004771092,0.000002584012,0.000003349488,0.000008854583,0.000003424951,0.9961029,0.002201605,0.001121065,0.0004944569,0.000004705218],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002148821,0.0000456166,0.997079,0.00003451739,0.00001094714,0.00001629364,0.00002086697,0.0002977341,0.0003461987],"genre_scores_gemma":[0.07169897,0.00009863321,0.9242691,0.0001033641,0.00003395302,0.0001464932,0.0002700176,0.0002649397,0.003114573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006758574,"threshold_uncertainty_score":0.01343846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03916382982208769,"score_gpt":0.3059089571069433,"score_spread":0.2667451272848556,"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."}}