{"id":"W4392628917","doi":"10.26868/25222708.2023.1378","title":"Inverse surrogate modelling to determine thermal characteristics of buildings","year":2023,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Mean squared error; Building envelope; Mean absolute percentage error; Computer science; Surrogate model; Inverse; Approximation error; Artificial neural network; Convolutional neural network; Algorithm; Machine learning; Statistics; Mathematics; Thermal","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":[0.0003451417,0.0005141415,0.0003994086,0.0003579976,0.0001315726,0.0006719154,0.0004273209,0.0006310531,0.001337951],"category_scores_gemma":[0.001612577,0.0003728893,0.0005742706,0.0004096508,0.0003231939,0.0007633243,0.0004663474,0.000632067,0.0003264793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003729643,"about_ca_system_score_gemma":0.0004549287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002860427,"about_ca_topic_score_gemma":0.002579148,"domain_scores_codex":[0.9998287,0.00004538769,0.000009868847,0.00003283657,0.00006808381,0.00001505826],"domain_scores_gemma":[0.9997343,0.0001338254,0.00003454155,0.0000387232,0.00004877578,0.000009762098],"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":[0.000008511191,0.000007803272,0.0004022881,0.00001282529,0.000004487919,0.00001120044,0.000007599674,0.9941633,0.001364182,0.0008043722,0.00007528479,0.003138053],"study_design_scores_gemma":[8.347786e-7,0.000004631346,0.0001499404,0.000001932072,8.258601e-7,0.000005232704,0.000002168061,0.9986812,0.0004775838,0.00050285,0.0001705757,0.000002116489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1448934,0.0002769078,0.8437436,0.0001648307,0.00004787694,0.00005813277,0.0006106414,0.0005288147,0.0096759],"genre_scores_gemma":[0.9606621,0.0002117795,0.03600422,0.00003300745,0.000009734204,0.00006800786,0.000536938,0.00005152567,0.002422817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002860427,"threshold_uncertainty_score":0.005687535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03736025903891525,"score_gpt":0.2458222608240025,"score_spread":0.2084620017850873,"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."}}