{"id":"W4414230370","doi":"10.1016/j.energy.2025.138470","title":"Few-shot and continuous online learning for forecasting in the energy industry","year":2025,"lang":"en","type":"article","venue":"Energy","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agência Nacional do Petróleo, Gás Natural e Biocombustíveis; Fundação de Amparo à Pesquisa do Estado de São Paulo; Computer Modelling Group","keywords":"Interpretability; Extrapolation; Normalization (sociology); Time series; Autoregressive integrated moving average; Range (aeronautics); Artificial neural network; Autoencoder; Energy (signal processing)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003117476,0.0008803164,0.002179011,0.001250587,0.0006669299,0.001615832,0.002284568,0.002323521,0.002060406],"category_scores_gemma":[0.01477827,0.001017135,0.0007985952,0.001524672,0.001670398,0.003962195,0.001311348,0.00324826,0.0003479705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001530181,"about_ca_system_score_gemma":0.001213974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0143376,"about_ca_topic_score_gemma":0.01200893,"domain_scores_codex":[0.9992734,0.0002749116,0.00004401494,0.0001930125,0.0001380363,0.00007672222],"domain_scores_gemma":[0.9917529,0.007040781,0.0003372356,0.0002816154,0.0003820484,0.0002054577],"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":[0.0001524786,0.0001191159,0.00124703,0.0001242114,0.00008160505,0.00005622084,0.00007600117,0.90249,0.0004491956,0.04471081,0.001895548,0.04859768],"study_design_scores_gemma":[0.000002557745,0.000004381217,0.0001015856,0.000003972552,0.000002929693,0.000003354368,0.000003117492,0.981701,0.0000656557,0.01801846,0.00008869096,0.00000450272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03891574,0.001995943,0.9557638,0.001136334,0.0001515983,0.00002501189,0.0001756883,0.0003610221,0.001474843],"genre_scores_gemma":[0.9065176,0.001388095,0.08594695,0.0002593826,0.0003596901,0.00007542792,0.0004844473,0.0001194721,0.004849051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0143376,"threshold_uncertainty_score":0.02850831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02477469569726127,"score_gpt":0.2589573903525069,"score_spread":0.2341826946552457,"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."}}