{"id":"W4385858713","doi":"10.22382/wfs-2023-10","title":"Fiber Quality Prediction Using Nir Spectral Data: Tree-Based Ensemble Learning VS Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"Wood and Fiber Science","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"U.S. Forest Service; National Science Foundation; University of Georgia; U.S. Department of Agriculture; U.S. Department of Energy; National Institute of Food and Agriculture","keywords":"Random forest; Artificial neural network; Gradient boosting; Artificial intelligence; Boosting (machine learning); Dimensionality reduction; Principal component analysis; Multilayer perceptron; Computer science; Extreme learning machine; Pattern recognition (psychology); Decision tree; Convolutional neural network; Machine learning; Support vector machine","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":[0.001658259,0.0009846344,0.001051663,0.0007951163,0.0002703149,0.000606427,0.0008127816,0.0007323512,0.0004635252],"category_scores_gemma":[0.001965209,0.0002677201,0.0008066469,0.0006147469,0.0001843226,0.001201276,0.0005207021,0.001201503,0.0002360545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004939695,"about_ca_system_score_gemma":0.0005609537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008498412,"about_ca_topic_score_gemma":0.009723033,"domain_scores_codex":[0.9997078,0.00007714202,0.0000191903,0.00008782589,0.00006058793,0.00004754241],"domain_scores_gemma":[0.9992839,0.0002942485,0.00006489539,0.0000760418,0.0002413126,0.0000396718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003765436,0.0003498397,0.01326502,0.00007696524,0.000287005,0.00007296296,0.0000590761,0.6767216,0.003527024,0.001181085,0.002167256,0.3019157],"study_design_scores_gemma":[0.000002812292,0.00002522328,0.0005813218,0.000005104058,0.00001477035,0.000004649545,0.000005273189,0.9985027,0.0003902251,0.0003703771,0.00009417045,0.000003334054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4825113,0.007134603,0.5026451,0.001063407,0.0003444895,0.00009704706,0.0006241053,0.001699814,0.003880226],"genre_scores_gemma":[0.9443262,0.0009517969,0.05220316,0.0001770993,0.0001055247,0.00004663042,0.0006578339,0.00003444916,0.001497401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008498412,"threshold_uncertainty_score":0.01689786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0655593283818961,"score_gpt":0.3278357918899483,"score_spread":0.2622764635080522,"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."}}