{"id":"W4413770817","doi":"10.1016/j.rsase.2025.101700","title":"Deep hyperspectral clustering using attention-enhanced 3D-2D convolutional autoencoder for mineral mapping","year":2025,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"Canadian Space Agency","keywords":"Autoencoder; Hyperspectral imaging; Cluster analysis; Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Environmental science; Geology; Deep learning","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":[0.0001792399,0.0001433593,0.0001401428,0.00002465921,0.0006244584,0.00006463648,0.0001480997,0.00009872402,0.000002965134],"category_scores_gemma":[0.00000862574,0.0001598384,0.0001169569,0.0001432573,0.0001192962,0.00008628021,0.0001712803,0.0001111812,0.000002787239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001646315,"about_ca_system_score_gemma":0.00003075691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001792865,"about_ca_topic_score_gemma":0.000001394418,"domain_scores_codex":[0.9989198,0.00001678565,0.0002142245,0.0004660233,0.0001067903,0.0002763853],"domain_scores_gemma":[0.9994627,0.00006727241,0.00008100297,0.0003053048,0.0000325687,0.0000511561],"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":[0.000009407781,0.0001005245,0.0000748513,0.0003506564,0.0002469489,0.000001114506,0.001929724,0.2469379,0.4628776,0.007459101,0.0003628266,0.2796493],"study_design_scores_gemma":[0.0002745414,0.000005674043,0.0004184783,0.00003695397,0.00002068465,0.00001452267,0.0003507697,0.9835978,0.0006600372,0.005305963,0.009155415,0.0001591943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005547591,0.0001970342,0.9899244,0.002982566,0.00005918296,0.0003357354,0.000001630878,0.00007546454,0.0008763918],"genre_scores_gemma":[0.1115271,0.00008072978,0.8870532,0.0003206972,0.00007248071,0.000004722831,0.00001421367,0.000003590612,0.0009232516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7366598,"threshold_uncertainty_score":0.6518021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01486716703218391,"score_gpt":0.2272100200936831,"score_spread":0.2123428530614992,"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."}}