{"id":"W4415053970","doi":"10.1016/j.rineng.2025.107599","title":"Harnessing machine learning for rapid and cost-efficient 3D geometry generation in neighborhood energy modeling","year":2025,"lang":"en","type":"article","venue":"Results in Engineering","topic":"3D Modeling in Geospatial Applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Energy modeling; Memory footprint; Footprint; Segmentation; Efficient energy use; 3D city models; Image processing; Artificial neural network; Ranging","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":[0.0003214132,0.0001892986,0.0002109569,0.0005619938,0.00006068095,0.00005266305,0.00009860901,0.0001183989,9.125466e-7],"category_scores_gemma":[0.0001890623,0.0002284378,0.00002859424,0.0005415482,0.000007210873,0.00007698058,0.00004267858,0.0002580782,3.945757e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001894617,"about_ca_system_score_gemma":0.00001846242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008961176,"about_ca_topic_score_gemma":0.00007995833,"domain_scores_codex":[0.9988158,0.00001180019,0.0004650938,0.0002948058,0.0000911804,0.0003213561],"domain_scores_gemma":[0.9996002,0.000122771,0.00002519639,0.0001738789,0.0000357417,0.00004226817],"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":[0.000008590839,0.00001517371,0.00004911014,0.00008513088,0.000009313525,7.437002e-7,0.0001663685,0.9560167,0.002854869,0.0005420326,0.000004748378,0.04024727],"study_design_scores_gemma":[0.0009196381,0.000008534972,0.00006117535,0.0001505243,0.000007709384,0.000001004527,0.00002123945,0.9970524,0.0009014483,0.00002633081,0.0006496915,0.0002003447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06426239,0.001859616,0.9329334,0.00004369085,0.0002059761,0.0002863695,0.00001267634,0.0002037498,0.0001921414],"genre_scores_gemma":[0.9861788,0.0002668628,0.0130443,0.0000121597,0.0000798804,0.0002547023,0.0001026064,0.00004213734,0.00001856819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9219164,"threshold_uncertainty_score":0.9315423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01399205476727228,"score_gpt":0.2304916364307102,"score_spread":0.216499581663438,"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."}}