{"id":"W4413422426","doi":"10.1016/j.jece.2025.118848","title":"Machine Learning-driven insights into catalytic hydrothermal liquefaction of nitrogen-rich biomass: Enhancing bio-oil yield and reducing nitrogen content","year":2025,"lang":"en","type":"article","venue":"Journal of environmental chemical engineering","topic":"Catalysis and Hydrodesulfurization Studies","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada; University of Prince Edward Island; Dalhousie University","funders":"Killam Trusts; Dalhousie University","keywords":"Nitrogen; Yield (engineering); Hydrothermal liquefaction; Biomass (ecology); Hydrothermal circulation; Liquefaction; Chemistry; Catalysis; Environmental science; Environmental chemistry; Chemical engineering; Materials science; Geology; Engineering; Oceanography; Organic chemistry; Metallurgy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00009328772,0.0001983944,0.0003872809,0.000244221,0.00004430693,0.00001682118,0.00009577308,0.00008899247,0.00001285652],"category_scores_gemma":[0.00006013696,0.000189192,0.000119706,0.0001604834,0.00004664652,0.0001593042,0.00007556776,0.0002915871,0.000001818675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002074818,"about_ca_system_score_gemma":0.000008143706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000142426,"about_ca_topic_score_gemma":0.000001376193,"domain_scores_codex":[0.9989253,0.000007379351,0.0005845482,0.0001375459,0.0001844003,0.0001608132],"domain_scores_gemma":[0.999592,0.00007825754,0.0001361094,0.00009722445,0.00001538308,0.00008100331],"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":[0.00001622158,0.0000344818,0.002550404,0.0001661359,0.000306096,0.000004823549,0.0003204501,0.04142839,0.9544076,0.000004391415,0.000005177242,0.0007558698],"study_design_scores_gemma":[0.0003777237,0.0000371254,0.0004123969,0.0002276174,0.0001077376,0.00002620042,0.0001323386,0.03616523,0.9621477,0.00001282714,0.000189583,0.0001635747],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989535,0.007200769,0.002967831,0.00002339472,0.0001104699,0.00004285345,0.000004589762,0.00003469507,0.00008038877],"genre_scores_gemma":[0.9987027,0.0008100504,0.0003480317,0.000006658332,0.00006596233,0.000003879658,0.000009194216,0.00002802467,0.00002547458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009167715,"threshold_uncertainty_score":0.7715025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006411282346775614,"score_gpt":0.1828062866461866,"score_spread":0.176395004299411,"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."}}