{"id":"W4391876367","doi":"10.1063/5.0168973","title":"Predicting wind farm wake losses with deep convolutional hierarchical encoder–decoder neural networks","year":2024,"lang":"en","type":"article","venue":"APL Machine Learning","topic":"Wind Energy Research and Development","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wake; Convolutional neural network; Computer science; Encoder; Environmental science; Artificial intelligence; Engineering; Aerospace 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":[],"consensus_categories":[],"category_scores_codex":[0.0002449806,0.0002506087,0.0001968595,0.0001529056,0.0002339767,0.00019836,0.0001582464,0.00009900759,0.0002455343],"category_scores_gemma":[0.00005937812,0.0002039912,0.00006238393,0.0003322213,0.00007862971,0.0001653715,0.00008614178,0.001333814,0.00003795712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008817507,"about_ca_system_score_gemma":0.00005461774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006525327,"about_ca_topic_score_gemma":0.0001650094,"domain_scores_codex":[0.998338,0.00006537679,0.0002392392,0.000325157,0.0003901997,0.0006419848],"domain_scores_gemma":[0.9993557,0.0002555448,0.0000162267,0.0001229502,0.00003489566,0.0002147243],"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":[0.00002819003,0.00001033551,0.03150773,0.00007119176,0.0001380103,0.0001556779,0.0002818892,0.9444423,0.00004908623,0.0004397655,0.000109672,0.02276609],"study_design_scores_gemma":[0.0002781441,0.00008314211,0.00824791,0.00008233936,0.00001356592,0.0001337216,0.00004306755,0.9814476,0.00003019831,0.00008324609,0.009303353,0.0002537302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7526344,0.009839052,0.2225575,0.0005545819,0.000802754,0.00022972,0.000009332748,0.002191822,0.01118081],"genre_scores_gemma":[0.996895,0.0001049318,0.00154333,0.00006226712,0.0005202864,0.00001998874,0.0001056836,0.00007814054,0.0006703896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2442606,"threshold_uncertainty_score":0.8318521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006263107066874245,"score_gpt":0.2129579584933886,"score_spread":0.2066948514265144,"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."}}