{"id":"W4413271117","doi":"10.1016/j.segan.2025.101865","title":"Forecasting electricity prices with deep learning and dynamic sparse training","year":2025,"lang":"en","type":"article","venue":"Sustainable Energy Grids and Networks","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Electricity; Training (meteorology); Artificial intelligence; Economics; Computer science; Engineering; Meteorology; Electrical engineering; Geography","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":[0.0002226624,0.0002540149,0.0002655472,0.0001784617,0.0004264582,0.0001404447,0.00007381643,0.0001326286,0.000004489179],"category_scores_gemma":[0.00002829274,0.000228433,0.00002751169,0.0005748841,0.00006387639,0.000194325,0.00006871925,0.0003480763,4.317251e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006516853,"about_ca_system_score_gemma":0.00002919443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009769732,"about_ca_topic_score_gemma":0.0001838826,"domain_scores_codex":[0.9986917,0.00002429135,0.0001982197,0.0002805487,0.00008338326,0.0007218522],"domain_scores_gemma":[0.9995505,0.0001629265,0.00004534958,0.00008586101,0.00005503936,0.0001003873],"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":[0.00003376128,0.000006588399,0.001977158,0.000165886,0.00009548256,0.00008057939,0.0003878502,0.7648736,0.0000207552,0.01226802,0.00003350951,0.2200568],"study_design_scores_gemma":[0.0003691947,0.00009564196,0.0002878394,0.0001470946,0.00003995408,0.0000364919,0.001693918,0.9806728,0.00004813235,0.0006790961,0.01564187,0.0002879314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5645155,0.02840365,0.3652002,0.00004123293,0.0002565561,0.0001355577,5.325479e-7,0.000574553,0.0408722],"genre_scores_gemma":[0.9951459,0.001681129,0.0007457741,0.00003969284,0.0001042763,0.00002366028,0.00001143801,0.00003970739,0.002208489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4306303,"threshold_uncertainty_score":0.9315227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004315526837164558,"score_gpt":0.1845054410618434,"score_spread":0.1801899142246788,"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."}}