{"id":"W4403426018","doi":"10.1016/j.energy.2024.133475","title":"Strategies for designing machine learning models in renewable energy with insufficient data","year":2024,"lang":"en","type":"article","venue":"Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Canada First Research Excellence Fund; University of Alberta","keywords":"Renewable energy; Computer science; Machine learning; Energy (signal processing); Artificial intelligence; Engineering; Electrical 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":[0.0001839982,0.0001973568,0.0001757868,0.0001940706,0.00006848881,0.0001693229,0.0002561116,0.00007113233,0.00001410529],"category_scores_gemma":[0.000007244872,0.0001733156,0.00002688364,0.0003441255,0.00001817039,0.0005147547,0.00006971564,0.0001338645,6.770049e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005066737,"about_ca_system_score_gemma":0.00007149993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002732235,"about_ca_topic_score_gemma":0.005788836,"domain_scores_codex":[0.998947,0.00002336427,0.0002074453,0.0003301198,0.0001274544,0.0003645991],"domain_scores_gemma":[0.9995209,0.0001231303,0.00001702874,0.0002682491,0.00001553864,0.00005515949],"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":[0.00001149338,0.000009916991,0.000009410533,0.00006083423,0.00003332831,0.00002769918,0.000265325,0.9543484,0.001283872,0.03645159,0.0005284937,0.006969587],"study_design_scores_gemma":[0.0001665441,0.00006157775,6.49261e-7,0.0002085613,0.00001034853,0.00001064717,0.0001652262,0.891958,0.002488101,0.002003301,0.1027128,0.0002142378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002859974,0.007872634,0.9617366,0.00001603647,0.0003028435,0.00002999618,0.00002420865,0.0005654711,0.02659229],"genre_scores_gemma":[0.991555,0.0002494155,0.006463674,0.00002291833,0.000147392,0.00004084691,0.0002961823,0.00008565601,0.001138859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9886951,"threshold_uncertainty_score":0.7067605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03717648067477077,"score_gpt":0.225327237017009,"score_spread":0.1881507563422382,"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."}}