{"id":"W2126255529","doi":"10.1109/whispers.2009.5289056","title":"The cost of time - implications of hyperspectral data volume and feature selection routines for conservation science","year":2009,"lang":"en","type":"article","venue":"","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hyperspectral imaging; Identification (biology); Feature selection; Selection (genetic algorithm); Volume (thermodynamics); Tropics; Computer science; Vegetation (pathology); Feature (linguistics); Remote sensing; Data science; Tree (set theory); Ecology; Data mining; Environmental science; Machine learning; Artificial intelligence; Geography; Biology; Mathematics","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":[0.006399557,0.0009233834,0.0007535517,0.002204641,0.001158481,0.00376246,0.001990254,0.0006543707,0.02195553],"category_scores_gemma":[0.03281537,0.0006445844,0.0009071119,0.004187848,0.001356443,0.004209427,0.001552704,0.00140519,0.01340135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00227291,"about_ca_system_score_gemma":0.001859554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008369132,"about_ca_topic_score_gemma":0.01232153,"domain_scores_codex":[0.9939971,0.002596116,0.0002987511,0.000606059,0.002240238,0.0002617649],"domain_scores_gemma":[0.945213,0.03757146,0.00189276,0.00791128,0.00646445,0.0009470865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002259139,0.0002769612,0.007036628,0.0004149819,0.0001203555,0.0004621661,0.001271485,0.02855854,0.02703292,0.02639251,0.04526701,0.8609073],"study_design_scores_gemma":[0.0008774366,0.001109313,0.06838681,0.0004443235,0.0003683355,0.002622265,0.006071572,0.5206259,0.07775793,0.1235959,0.1977433,0.0003969084],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2045571,0.002748276,0.6649124,0.02625172,0.00110737,0.001107317,0.005069639,0.02562758,0.06861868],"genre_scores_gemma":[0.3956518,0.001201399,0.5683013,0.001476575,0.0005793643,0.0007366406,0.003795412,0.004076639,0.02418079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02195553,"threshold_uncertainty_score":0.07344854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03520697119222591,"score_gpt":0.2891609178350798,"score_spread":0.2539539466428539,"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."}}