{"id":"W3198644427","doi":"10.1038/s41598-021-96850-2","title":"Rapid identification of wood species using XRF and neural network machine learning","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Canada; Parks Canada","funders":"Andrew W. Mellon Foundation","keywords":"Identification (biology); Convolutional neural network; Species identification; Artificial neural network; Computer science; Machine learning; Artificial intelligence; Biochemical engineering; Engineering; Ecology; Biology","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":[0.001019211,0.0001065098,0.0001861297,0.0000612072,0.0004068433,0.0003259386,0.00008899968,0.00006007553,0.0007615722],"category_scores_gemma":[0.0002988362,0.0001004259,0.00007572533,0.0004609743,0.0002464946,0.000135951,0.0001781214,0.0002173457,0.000002152822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000216108,"about_ca_system_score_gemma":0.000109914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001449403,"about_ca_topic_score_gemma":0.00001000058,"domain_scores_codex":[0.9980692,0.00004952506,0.0005122864,0.0005574147,0.0005134022,0.000298141],"domain_scores_gemma":[0.9988003,0.0000462446,0.000313821,0.0005152319,0.0002325207,0.00009181681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004073921,0.00003707366,0.01613753,0.0001159964,0.00002034706,0.0002826139,0.0001600806,0.001060494,0.9787835,0.00002436967,0.000622204,0.002751742],"study_design_scores_gemma":[0.0001382149,0.000007652979,0.001262053,0.00009511637,0.00002955604,0.0005639648,0.0003727458,0.01372395,0.9641476,0.0008512075,0.0186317,0.0001762734],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929019,0.002751437,0.00003982523,0.0000796797,0.001180783,0.00004281644,0.000003252155,0.00003602755,0.002964323],"genre_scores_gemma":[0.9809473,0.00003834664,0.0002038636,0.000003277622,0.0001816419,0.000002066527,0.00009189553,0.00001381287,0.01851776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01800949,"threshold_uncertainty_score":0.8338681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03362267976593017,"score_gpt":0.2733155971810923,"score_spread":0.2396929174151621,"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."}}