{"id":"W4296668464","doi":"10.1002/cjce.24674","title":"Prediction of bio‐oil yield during pyrolysis of lignocellulosic biomass using machine learning algorithms","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Thermochemical Biomass Conversion Processes","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Overfitting; Machine learning; Pyrolysis; Biomass (ecology); Mean squared error; Gradient boosting; Boosting (machine learning); Algorithm; Random forest; Artificial intelligence; Computer science; Mathematics; Engineering; Statistics; Agronomy; Waste management; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002651675,0.00016334,0.0003116259,0.000348688,0.000088083,0.00001370691,0.0004098144,0.00007621614,0.0001554271],"category_scores_gemma":[0.0001558379,0.0001530969,0.0001596913,0.0006095617,0.00006404989,0.00009462123,0.00005247165,0.0005622509,4.151003e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003283502,"about_ca_system_score_gemma":0.000127083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005787617,"about_ca_topic_score_gemma":0.0000110556,"domain_scores_codex":[0.9987562,0.00001680084,0.0005418461,0.00009558981,0.0003105198,0.0002789983],"domain_scores_gemma":[0.9992359,0.000102246,0.0001928986,0.000146051,0.00009518467,0.0002277629],"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":[0.00001067371,0.000006192097,0.0004006143,0.0002041692,0.0001236585,0.00001504936,0.0002063091,0.06204385,0.9367186,0.0000056025,0.000009824013,0.0002554708],"study_design_scores_gemma":[0.0002378835,0.00002665656,0.00002717178,0.00009929761,0.0000735273,0.0001332612,0.00004593154,0.04705243,0.9520861,0.00001039271,0.0000906139,0.0001167327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974037,0.001960917,0.0001808697,0.00005350052,0.0002635132,0.00002993472,0.00004766966,0.00003521222,0.00002468286],"genre_scores_gemma":[0.999487,0.00001145158,0.0003532845,0.000003798388,0.00008538217,0.000002079096,0.00000441991,0.00004225528,0.00001029328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01536751,"threshold_uncertainty_score":0.6243111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01098495700995671,"score_gpt":0.167099791480132,"score_spread":0.1561148344701753,"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."}}