{"id":"W3047631606","doi":"10.1016/j.apenergy.2020.115563","title":"Using a deep temporal convolutional network as a building energy surrogate model that spans multiple climate zones","year":2020,"lang":"en","type":"article","venue":"Applied Energy","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"Canarie","keywords":"Surrogate model; Convolutional neural network; Building energy simulation; Computer science; Process (computing); Sensitivity (control systems); Model building; Building design; Building model; Machine learning; Artificial neural network; Efficient energy use; Artificial intelligence; Simulation; Engineering; Architectural 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006992672,0.00031132,0.0002958681,0.00006365741,0.0002231741,0.00005619952,0.0002104881,0.00018749,0.00003300128],"category_scores_gemma":[0.000004864449,0.000349658,0.00009544369,0.0003363275,0.00004361567,0.0001583897,0.0001092885,0.0001325171,0.000002900553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007689038,"about_ca_system_score_gemma":0.00003569288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002237234,"about_ca_topic_score_gemma":0.0001421319,"domain_scores_codex":[0.9985372,0.00001762408,0.0002855906,0.0003568,0.0002302343,0.0005725091],"domain_scores_gemma":[0.9994714,0.00004674548,0.00007421912,0.0001946863,0.0000271567,0.000185777],"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":[0.00004124514,0.00001235749,0.0001381053,0.00001556205,0.00005428755,0.000004354942,0.00004767542,0.7992292,0.002005555,0.1975399,0.0001489197,0.0007628514],"study_design_scores_gemma":[0.000479635,0.00001292868,0.000007780495,0.00001840876,0.00003030304,0.000006909169,0.00002301387,0.988895,0.003524457,0.003615858,0.002995431,0.0003903047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03819805,0.0003568064,0.9579691,0.00004660745,0.0002272404,0.00004615042,0.000009416583,0.0007106178,0.00243607],"genre_scores_gemma":[0.9372728,0.0001947916,0.06127097,0.0006001653,0.0003672846,0.00004994189,0.0001267979,0.00009786674,0.00001938007],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8990747,"threshold_uncertainty_score":0.9998955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02673542658388631,"score_gpt":0.208279538410277,"score_spread":0.1815441118263907,"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."}}