{"id":"W4224119702","doi":"10.1002/elsa.202100185","title":"Accurately predicting transport properties of porous fibrous materials by machine learning methods","year":2022,"lang":"en","type":"article","venue":"Electrochemical Science Advances","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thermal diffusivity; Support vector machine; Gradient boosting; Permeability (electromagnetism); Porosity; Artificial neural network; Computer science; Artificial intelligence; Mass transport; Biological system; Electrolyte; Materials science; Porous medium; Regression; Machine learning; Membrane; Chemistry; Composite material; Mathematics; Statistics; Random forest; Engineering; Physics; Thermodynamics; Biochemical engineering","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":[0.0007234056,0.0001544782,0.0002659806,0.00006011951,0.0002724016,0.00002566891,0.0003905927,0.00003945759,0.0002441916],"category_scores_gemma":[0.00006224695,0.0001263436,0.00003127631,0.0004854412,0.0001986676,0.0003186802,0.0000639145,0.0002491309,0.00000135623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008204635,"about_ca_system_score_gemma":0.00003577911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000223211,"about_ca_topic_score_gemma":5.064654e-7,"domain_scores_codex":[0.998519,0.00005766283,0.0003538198,0.0002649209,0.0003531991,0.0004514132],"domain_scores_gemma":[0.9996688,0.00003309839,0.00009053626,0.0001082606,0.0000323815,0.00006693798],"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":[0.00003978778,0.0000164398,0.00003959041,0.0001787002,0.000008625661,0.000001359871,0.0002088619,0.005363034,0.9930822,0.000005093606,0.000007617557,0.001048647],"study_design_scores_gemma":[0.0001150982,0.0001184919,0.000003965341,0.00001727657,0.00001016895,0.00002214057,0.00007867064,0.002112225,0.9939579,0.00009687465,0.003303953,0.0001632566],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773285,0.0206665,0.0003436593,0.00002265729,0.0003376341,0.0001405063,0.0000159122,0.0002345408,0.0009100335],"genre_scores_gemma":[0.9966454,0.0008134495,0.002363505,0.00001166726,0.00003006971,0.00003782764,0.00001665334,0.00002200919,0.00005940444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01985305,"threshold_uncertainty_score":0.5152141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00978925184812256,"score_gpt":0.2501576819452567,"score_spread":0.2403684300971342,"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."}}