{"id":"W4387359966","doi":"10.1080/17480272.2023.2265349","title":"A chemistry-based explainable machine learning model based on NIR spectra for predicting wood properties and understanding wavelength selection","year":2023,"lang":"en","type":"article","venue":"Wood Material Science and Engineering","topic":"Wood Treatment and Properties","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Random forest; Surface roughness; Western Hemlock; Spectral line; Near-infrared spectroscopy; Wavelength; Overtone; Tsuga; Mathematics; Soil science; Biological system; Machine learning; Artificial intelligence; Remote sensing; Materials science; Analytical Chemistry (journal); Chemistry; Computer science; Environmental science; Composite material; Geology; Botany; Optics; Physics; Environmental chemistry; Optoelectronics","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":[0.0007047924,0.0006174354,0.0004566294,0.0005614846,0.0002598636,0.0005950298,0.0008089969,0.0006919516,0.0007947705],"category_scores_gemma":[0.001374875,0.0003343121,0.00071715,0.0004130796,0.0003745081,0.001001305,0.0002855544,0.0008457869,0.0002089488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006112552,"about_ca_system_score_gemma":0.0005910204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005183389,"about_ca_topic_score_gemma":0.005235438,"domain_scores_codex":[0.9998726,0.00003333666,0.000006309662,0.00004602587,0.00002653203,0.00001517425],"domain_scores_gemma":[0.9995785,0.0002566173,0.00006070617,0.00002891158,0.00006340475,0.00001188267],"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":[0.00005092089,0.0000828951,0.004952388,0.00004778468,0.00008514381,0.00007762901,0.00004293935,0.9650103,0.00816813,0.005222084,0.0003841125,0.01587557],"study_design_scores_gemma":[0.000002710625,0.00001244704,0.0007004525,0.000001485265,0.000007120851,0.00000858973,0.000002159313,0.9966416,0.0004832072,0.001993726,0.0001411731,0.0000052437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.247556,0.0004597807,0.747041,0.0005312706,0.00008367889,0.00009270901,0.0004909022,0.0006928031,0.003051955],"genre_scores_gemma":[0.9260683,0.000270356,0.07065333,0.0001252886,0.00004425697,0.0001599629,0.0003490235,0.00005118645,0.002278238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005183389,"threshold_uncertainty_score":0.01030648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701932284491797,"score_gpt":0.1890815160773097,"score_spread":0.1620621932323918,"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."}}