{"id":"W4405124246","doi":"10.1007/s00226-024-01615-5","title":"Transfer learning for predicting wood density of different tree species: calibration transfer from portable NIR spectrometer to hyperspectral imaging","year":2024,"lang":"en","type":"article","venue":"Wood Science and Technology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities","keywords":"Hyperspectral imaging; Transfer of learning; Artificial intelligence; Calibration; Computer science; Spectrometer; Artificial neural network; Tree (set theory); Near-infrared spectroscopy; Remote sensing; Overfitting; Biological system; Machine learning; Pattern recognition (psychology); Environmental science; Mathematics; Optics; Statistics; Geology; Physics","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":[0.0009509175,0.0009639104,0.0004148854,0.0007332877,0.000305429,0.000379942,0.0008628083,0.0007448653,0.001234756],"category_scores_gemma":[0.002317211,0.0002487504,0.0006495132,0.000948226,0.000396003,0.0009160527,0.0008447946,0.000976951,0.0007041701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004974403,"about_ca_system_score_gemma":0.0004141992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003823519,"about_ca_topic_score_gemma":0.002766494,"domain_scores_codex":[0.9997713,0.00005903776,0.000009431397,0.0000767224,0.00005720576,0.00002629589],"domain_scores_gemma":[0.999355,0.0003091126,0.00005951961,0.00009043239,0.0001613921,0.0000243963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002744168,0.0004833719,0.009183856,0.0001097332,0.0001522068,0.00008696268,0.0001337541,0.3669139,0.04009663,0.001062281,0.00206375,0.579439],"study_design_scores_gemma":[0.000005707444,0.00004778762,0.002713646,0.000003975022,0.00001532172,0.0000257847,0.00002646679,0.9859245,0.009365294,0.001593357,0.0002668788,0.00001116653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3557158,0.0004323793,0.6388596,0.0001647259,0.00007192309,0.00008958582,0.0003075306,0.002375002,0.001983474],"genre_scores_gemma":[0.9246361,0.0001829297,0.07214978,0.00006769246,0.00003146875,0.00009358351,0.0004107673,0.0000890755,0.0023387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003823519,"threshold_uncertainty_score":0.007602513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01086325854920856,"score_gpt":0.2430200457199615,"score_spread":0.2321567871707529,"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."}}