{"id":"W4389992248","doi":"10.1016/j.energy.2023.130061","title":"A novel machine learning framework for designing high-performance catalysts for production of clean liquid fuels through Fischer-Tropsch synthesis","year":2023,"lang":"en","type":"article","venue":"Energy","topic":"Catalysts for Methane Reforming","field":"Chemical Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; CRC Health Group","keywords":"Fischer–Tropsch process; Selectivity; Catalysis; Principal component analysis; Process engineering; Carbon fibers; Chemistry; Computer science; Biochemical engineering; Engineering; Artificial intelligence; Organic chemistry; Algorithm","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":[0.0004656076,0.0002516726,0.0004348543,0.0001688843,0.0001601589,0.00000983598,0.0002400305,0.0001948546,0.00000620408],"category_scores_gemma":[0.002195585,0.0002407118,0.000180713,0.0006208922,0.00004536213,0.0002813854,0.0000899318,0.0002197627,0.000005277347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001105221,"about_ca_system_score_gemma":0.00003427093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003358661,"about_ca_topic_score_gemma":0.00001612003,"domain_scores_codex":[0.9983614,0.00001711767,0.000453927,0.0004291787,0.0002365126,0.000501849],"domain_scores_gemma":[0.9985592,0.0006936531,0.0002194639,0.0003540618,0.0001120868,0.00006154278],"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":[0.0003046588,0.00004150609,0.00002595858,0.0005870477,0.0001573123,6.942839e-7,0.0005106942,0.03161428,0.9475266,0.004772769,0.00004007086,0.01441835],"study_design_scores_gemma":[0.0003038681,0.0001449094,0.00001130266,0.0002993254,0.00008418573,0.000007528994,0.0001460825,0.0239398,0.9715987,0.0002708203,0.002917423,0.0002760241],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5984116,0.0001448089,0.3999702,0.0001577307,0.0005041032,0.0002701227,0.00003223243,0.0004372966,0.00007189859],"genre_scores_gemma":[0.9481105,0.0000706014,0.0494983,0.00001247901,0.0005345157,0.0004615991,0.0001942685,0.0001307218,0.000987074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3504719,"threshold_uncertainty_score":0.9815943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02402022521504815,"score_gpt":0.2546950387064357,"score_spread":0.2306748134913875,"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."}}