{"id":"W4409178291","doi":"10.1038/s41598-025-95891-1","title":"Parallel boosting neural network with mutual information for day-ahead solar irradiance forecasting","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Solar Radiation and Photovoltaics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Uppsala Universitet","keywords":"Computer science; Boosting (machine learning); Random forest; Gradient boosting; Feature selection; Solar irradiance; Artificial neural network; Machine learning; Artificial intelligence; Mean absolute percentage error; Data mining; Decision tree; Information gain ratio; Feed forward; Feedforward neural network","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001120728,0.000641182,0.0009854387,0.0005192321,0.000312045,0.0005274105,0.0008901873,0.0005264294,0.0008603791],"category_scores_gemma":[0.001741924,0.0003623934,0.0006486446,0.0005125338,0.0002279583,0.0007534784,0.0005128146,0.0008382968,0.0002757364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006002894,"about_ca_system_score_gemma":0.0008485322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009170528,"about_ca_topic_score_gemma":0.006817504,"domain_scores_codex":[0.9996895,0.00006742878,0.00002042481,0.00006677974,0.0001058695,0.00005020563],"domain_scores_gemma":[0.9996074,0.0001422982,0.0000458536,0.00002648165,0.0001587534,0.00001929173],"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":[0.000159321,0.0001116355,0.002146113,0.00005003753,0.0000728471,0.00005747937,0.00002405177,0.8651766,0.002133473,0.0009425889,0.00186018,0.1272657],"study_design_scores_gemma":[0.000002563439,0.00001056562,0.0001946008,0.000001730904,0.000004747567,0.000002981431,0.000001203205,0.999209,0.0002141144,0.000254999,0.0001016052,0.000001890728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1782969,0.003062182,0.8079976,0.0006129789,0.0003541349,0.0001348313,0.0003282345,0.002366966,0.006846157],"genre_scores_gemma":[0.9473788,0.000465495,0.04970586,0.0001194849,0.00008556052,0.00007803573,0.0003686423,0.00004055508,0.001757465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009170528,"threshold_uncertainty_score":0.01823431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02084553384731198,"score_gpt":0.2392398925016549,"score_spread":0.2183943586543429,"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."}}