{"id":"W4385242124","doi":"10.1016/j.energy.2023.128546","title":"Yield prediction and optimization of biomass-based products by multi-machine learning schemes: Neural, regression and function-based techniques","year":2023,"lang":"en","type":"article","venue":"Energy","topic":"Thermochemical Biomass Conversion Processes","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Biofuel; Biomass (ecology); Pyrolysis; Yield (engineering); Radial basis function; Overfitting; Bioenergy; Artificial neural network; Mathematics; Pulp and paper industry; Biological system; Process engineering; Environmental science; Computer science; Machine learning; Engineering; Materials science; Waste management; Agronomy","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":[0.00006791243,0.0001191859,0.0001091778,0.0001453522,0.00005325653,0.00001389244,0.00004179755,0.00009881585,0.00001984504],"category_scores_gemma":[0.000136086,0.0001076405,0.00001389973,0.0003832239,0.00004256495,0.00009553965,0.00002038447,0.00006980143,3.916735e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001307522,"about_ca_system_score_gemma":0.000009446748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002135597,"about_ca_topic_score_gemma":0.000001114919,"domain_scores_codex":[0.9994387,0.00001743785,0.0001454568,0.0001887314,0.0001033001,0.0001063757],"domain_scores_gemma":[0.9996862,0.00007191413,0.00004905914,0.00009573417,0.00005456766,0.00004245704],"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":[0.00002845892,0.00001483615,0.000541101,0.0002002446,0.000009262248,6.266969e-7,0.000009752102,0.01665807,0.9758286,0.000003320322,0.000651349,0.006054389],"study_design_scores_gemma":[0.0001658563,0.00004492064,0.00002861539,0.00006409512,0.0000076109,3.128952e-7,0.000006633263,0.3616535,0.6367143,0.000001729989,0.00124792,0.00006449445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8354567,0.003669596,0.1565016,0.0004920331,0.000269036,0.0002228479,0.00005354541,0.003270842,0.00006385722],"genre_scores_gemma":[0.9964572,0.0001732102,0.003003186,0.00002127291,0.0000158485,0.00002136353,0.0002016874,0.00002814186,0.00007810183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3449954,"threshold_uncertainty_score":0.4389451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01055532443621461,"score_gpt":0.2049298630318815,"score_spread":0.1943745385956669,"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."}}