{"id":"W4416091520","doi":"10.1016/j.renene.2025.124738","title":"Multi-step short-term solar energy forecasting using Fourier-enhanced BiLSTM and neural additive models","year":2025,"lang":"en","type":"article","venue":"Renewable Energy","topic":"Solar Radiation and Photovoltaics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Robustness (evolution); Artificial neural network; Data pre-processing; Mean squared error; Benchmark (surveying); Generalization; Preprocessor; Mean absolute percentage error","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":[0.0004486422,0.0007650123,0.0004565867,0.0003482176,0.0002181551,0.000590337,0.0008456893,0.0005303685,0.001021557],"category_scores_gemma":[0.00112803,0.0002556328,0.0005580686,0.0003862239,0.0002084293,0.0009413958,0.0005420798,0.0009998231,0.0003549235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003695395,"about_ca_system_score_gemma":0.0005941528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008983344,"about_ca_topic_score_gemma":0.01163761,"domain_scores_codex":[0.9998711,0.00001720303,0.000009882772,0.00003817705,0.00004367005,0.00001993873],"domain_scores_gemma":[0.9997994,0.00006650438,0.00002480617,0.00002170846,0.00007381815,0.0000138455],"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":[0.00009514322,0.00007591008,0.00199435,0.00007603209,0.00006965136,0.000140774,0.00005938158,0.8620802,0.008981024,0.003436932,0.001350641,0.12164],"study_design_scores_gemma":[8.360618e-7,0.000006312115,0.00009896623,0.00000163382,0.00000243584,0.000005538089,0.000001676674,0.9990019,0.0003833687,0.0003784586,0.0001167873,0.000002142097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.125765,0.000929745,0.8660721,0.000399293,0.0002185316,0.00003517951,0.0003009708,0.001903502,0.004375713],"genre_scores_gemma":[0.9438735,0.0002791062,0.05335054,0.0000885107,0.00004426508,0.00003365413,0.000343375,0.00006264174,0.001924359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008983344,"threshold_uncertainty_score":0.01786208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04338813708809081,"score_gpt":0.2594735373616142,"score_spread":0.2160854002735234,"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."}}