{"id":"W2980221931","doi":"10.3390/en12203855","title":"Intelligent Estimation of Vitrinite Reflectance of Coal from Photomicrographs Based on Machine Learning","year":2019,"lang":"en","type":"article","venue":"Energies","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities","keywords":"Maceral; Vitrinite; Artificial intelligence; Coal; Computer science; Pattern recognition (psychology); Mean squared error; Cluster analysis; Support vector machine; Random forest; Data mining; Statistics; Mathematics; Engineering","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":[0.0005597034,0.0004575257,0.0004437683,0.001211871,0.0001781666,0.0005378041,0.000620719,0.0004650308,0.0005283333],"category_scores_gemma":[0.001159976,0.000280551,0.0004791223,0.0004841775,0.0002322085,0.0006328368,0.0003037922,0.000334256,0.0003728276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004162105,"about_ca_system_score_gemma":0.0003652622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002604991,"about_ca_topic_score_gemma":0.005157178,"domain_scores_codex":[0.999697,0.00004592484,0.00001336178,0.0001201757,0.00009731306,0.00002624251],"domain_scores_gemma":[0.9995281,0.000161683,0.00008851341,0.00005906552,0.0001447361,0.00001791834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002931503,0.0001908346,0.02421167,0.0002493338,0.0001066341,0.0001688252,0.0001470413,0.2015604,0.2007179,0.000849921,0.001330265,0.570174],"study_design_scores_gemma":[0.000004109384,0.00002826565,0.00855541,0.000005456539,0.00001209229,0.00006374448,0.00001601028,0.9621424,0.02849503,0.0003319109,0.0003311074,0.00001450629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2027731,0.0002984651,0.79227,0.00007563086,0.00002181206,0.00005509466,0.0001338421,0.002944337,0.001427738],"genre_scores_gemma":[0.7552783,0.0001828322,0.2431828,0.00003425885,0.00001481337,0.00004544512,0.0001979704,0.0001015915,0.0009618214],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002604991,"threshold_uncertainty_score":0.005179584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009777238484374255,"score_gpt":0.2249803337874907,"score_spread":0.2152030953031164,"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."}}