{"id":"W4400531588","doi":"10.3390/rs16142549","title":"Ensemble Band Selection for Quantification of Soil Total Nitrogen Levels from Hyperspectral Imagery","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Fondation OCP; Université Mohammed VI Polytechnique","keywords":"Hyperspectral imaging; VNIR; Environmental science; Remote sensing; Partial least squares regression; Context (archaeology); Kriging; Multivariate statistics; Soil science; Mathematics; Statistics; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347872,0.00007413678,0.00009381314,0.00003119752,0.000074711,0.0000459056,0.00002650274,0.00003923482,0.00003333696],"category_scores_gemma":[0.00005525895,0.00007645703,0.00005201068,0.0001335656,0.00003928655,0.00008066955,0.00001491456,0.0000545195,0.00003677862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008842485,"about_ca_system_score_gemma":0.00001619859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001938723,"about_ca_topic_score_gemma":0.000129116,"domain_scores_codex":[0.9993409,0.0000177057,0.0001465863,0.0002277831,0.0001171889,0.0001498596],"domain_scores_gemma":[0.9997063,0.0001227462,0.00003957625,0.00008681455,0.0000139611,0.00003063191],"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":[0.000008281409,0.000003964321,0.00005577496,0.00001502445,0.00001453044,0.000001991867,0.0002516771,0.001335982,0.8591729,0.00005028499,0.0003080691,0.1387815],"study_design_scores_gemma":[0.00008120697,0.00001873769,0.001286294,0.00004149086,0.00002998953,0.00001756728,0.00008174805,0.6708715,0.3177927,0.009407069,0.0002769958,0.00009469804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6927571,0.00006496563,0.3058564,0.00007891752,0.0001853131,0.00008966933,0.00001829026,0.00003402417,0.0009152969],"genre_scores_gemma":[0.9447935,0.000005605135,0.05489537,0.00001597995,0.00009633414,3.175141e-8,0.00001764632,0.00001417952,0.0001613971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6695355,"threshold_uncertainty_score":0.3117827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0243311384546176,"score_gpt":0.2553755523222592,"score_spread":0.2310444138676416,"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."}}