{"id":"W2901144234","doi":"10.1109/lgrs.2018.2877734","title":"Constrained Nonnegative Tensor Factorization for Spectral Unmixing of Hyperspectral Images: A Case Study of Urban Impervious Surface Extraction","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Matrix decomposition; Multilinear map; Data cube; Endmember; Pixel; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics; Tensor (intrinsic definition); Tucker decomposition; Cube (algebra); Spectral signature; Remote sensing; Geography; Data mining; Combinatorics; Tensor decomposition","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002531634,0.0001882729,0.0002568794,0.0001575834,0.0001835753,0.00004997135,0.00006775826,0.00006324194,5.893588e-7],"category_scores_gemma":[0.00009427812,0.0001832841,0.00005111943,0.0003670311,0.000498647,0.0002605523,0.000008404783,0.0001193679,5.981055e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008503976,"about_ca_system_score_gemma":0.00002737583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000789859,"about_ca_topic_score_gemma":0.0000725586,"domain_scores_codex":[0.9987543,0.00005027207,0.0003631634,0.0003339702,0.000201135,0.0002971729],"domain_scores_gemma":[0.99916,0.0001478783,0.0001742156,0.0002303248,0.0002246588,0.00006296037],"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":[0.00001885691,0.00002237041,0.00006456286,0.00004223816,0.00002318425,0.00005849912,0.006853184,0.001245106,0.9801342,9.198282e-7,0.00004115858,0.01149568],"study_design_scores_gemma":[0.0008076433,0.0003439612,0.001838692,0.0001060443,0.0000727109,0.0009270028,0.01014646,0.5966359,0.388818,0.00001890627,0.000006934078,0.0002777705],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.685537,0.000009659195,0.3134705,0.00007751107,0.0004608785,0.0003434328,0.000006650849,0.00006645486,0.00002788123],"genre_scores_gemma":[0.9184507,0.000006556048,0.08133431,0.00002695096,0.0001427579,6.002301e-8,0.00000185769,0.00002458223,0.00001224009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5953908,"threshold_uncertainty_score":0.747411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01903790819419885,"score_gpt":0.260746831285241,"score_spread":0.2417089230910422,"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."}}