{"id":"W4396664941","doi":"10.1016/j.ijhydene.2024.04.230","title":"Advancing hydrogen storage predictions in metal-organic frameworks: A comparative study of LightGBM and random forest models with data enhancement","year":2024,"lang":"en","type":"article","venue":"International Journal of Hydrogen Energy","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; University of Alberta; Memorial University of Newfoundland","funders":"","keywords":"Hydrogen storage; Random forest; Environmental science; Computer science; Hydrogen; Environmental chemistry; Materials science; Chemistry; Machine learning; Organic chemistry","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":[0.0004430911,0.0002072341,0.0004622904,0.0002654073,0.00004899562,0.0000842816,0.0008637842,0.0001265126,0.0003223067],"category_scores_gemma":[0.00005060867,0.0001627441,0.00007594423,0.0002570742,0.00006293783,0.0005296922,0.0002419209,0.0004738299,0.000001522984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001245563,"about_ca_system_score_gemma":0.0001472328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001324543,"about_ca_topic_score_gemma":0.0005988893,"domain_scores_codex":[0.9977828,0.00005731615,0.0008385358,0.00034879,0.0007998242,0.0001727629],"domain_scores_gemma":[0.9985542,0.0003275133,0.0004077321,0.0004122591,0.0001951288,0.0001031478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001753408,0.009999546,0.003197559,0.0002568934,0.0199375,0.001034653,0.01781099,0.5087041,0.3939825,0.02981962,0.001059451,0.01244378],"study_design_scores_gemma":[0.0056633,0.0005370578,0.00008541603,0.002390266,0.00111016,0.0005945635,0.007370709,0.7416669,0.2212819,0.01049135,0.0081366,0.0006716987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9156436,0.004002797,0.07934394,0.0003530533,0.0001229536,0.00009514279,0.00005967389,0.00001765892,0.0003612364],"genre_scores_gemma":[0.9978864,0.0006366064,0.001054911,0.00002524574,0.0002034408,0.00003114604,0.00003490385,0.00003007981,0.00009732335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2329629,"threshold_uncertainty_score":0.6636511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0201209490006647,"score_gpt":0.2797883652351236,"score_spread":0.2596674162344589,"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."}}