{"id":"W4409170517","doi":"10.1016/j.apenergy.2025.125812","title":"Improved surrogate modeling for multi-energy system design: Model architecture, sampling and scaling choices","year":2025,"lang":"en","type":"article","venue":"Applied Energy","topic":"Integrated Energy Systems Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Surrogate model; Scaling; Architecture; Sampling (signal processing); Computer science; Reliability engineering; Engineering; Mathematics; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002221869,0.0003864782,0.0004127456,0.0003147284,0.0002111373,0.000117141,0.000201944,0.0002796834,5.003334e-7],"category_scores_gemma":[0.00001461621,0.0003886871,0.00007448714,0.000290928,0.00002448912,0.00009353294,0.00004770132,0.0001302528,3.300677e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001735104,"about_ca_system_score_gemma":0.00004612454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005163472,"about_ca_topic_score_gemma":0.0002045163,"domain_scores_codex":[0.9984213,0.00002585738,0.0005042789,0.0004599977,0.0001087369,0.000479799],"domain_scores_gemma":[0.9993274,0.0001157952,0.00006531973,0.0002944313,0.0001062045,0.00009080728],"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":[0.00003597099,0.00000888457,3.985517e-7,0.0002087113,0.0001047847,2.596645e-7,0.00005752789,0.895247,0.01703583,0.08147679,0.00001002165,0.005813849],"study_design_scores_gemma":[0.0008032935,0.000008536955,1.572605e-7,0.0001588008,0.00005220558,0.000002264198,0.000121745,0.9765321,0.02090969,0.0007887452,0.0002737715,0.0003486795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001367223,0.0006844413,0.9943442,0.00000573131,0.0003242823,0.0002109794,0.00001164262,0.0008777064,0.002173823],"genre_scores_gemma":[0.7848858,0.00006289985,0.2140389,0.00005241107,0.00008622238,0.0005025909,0.00005638628,0.00009952987,0.0002153027],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7835186,"threshold_uncertainty_score":0.9998565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02499237222384672,"score_gpt":0.2326709411497651,"score_spread":0.2076785689259183,"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."}}