{"id":"W4404721189","doi":"10.2139/ssrn.5034412","title":"Improved Surrogate Modeling for Multi-Energy System Design: Model Architecture, Sampling and Scaling Choices","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Architecture; Surrogate model; Computer science; Scaling; Sampling (signal processing); Energy (signal processing); Statistics; Mathematics; Machine learning; Telecommunications; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00239554,0.0007224755,0.001306606,0.0004191585,0.0002714609,0.001005247,0.0008656943,0.001059826,0.002088845],"category_scores_gemma":[0.009695929,0.0006078532,0.0008012455,0.0006870247,0.0004583247,0.001421495,0.0008802983,0.001689728,0.0003267805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000449664,"about_ca_system_score_gemma":0.0007270949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001256392,"about_ca_topic_score_gemma":0.001437966,"domain_scores_codex":[0.9991296,0.000542218,0.00003230177,0.00005885482,0.0001994437,0.00003760062],"domain_scores_gemma":[0.9975533,0.001610953,0.0001467263,0.0002904825,0.000349541,0.00004900134],"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":[0.00003942178,0.0000202684,0.0001596801,0.00003550866,0.00001352228,0.00001535149,0.00001321055,0.9785697,0.0008320384,0.01106636,0.0002066295,0.009028165],"study_design_scores_gemma":[0.000002461179,0.000007063615,0.0000164743,0.000002471261,0.000001961641,0.000002491447,7.57567e-7,0.9973525,0.0001105561,0.00240625,0.00009592934,0.000001050424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006640115,0.0001153673,0.9917091,0.0001045283,0.00001573703,0.00001290634,0.00002947644,0.00009596181,0.001276892],"genre_scores_gemma":[0.6697972,0.0003873094,0.3260461,0.0001223983,0.00005841494,0.0002133242,0.0002228309,0.0002228685,0.002929553],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00239554,"threshold_uncertainty_score":0.01266897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04454362174318283,"score_gpt":0.2832129554226608,"score_spread":0.238669333679478,"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."}}