{"id":"W4412571399","doi":"10.1038/s41597-025-05575-8","title":"A high-resolution database of historical and future climate for Africa developed with deep neural networks","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of British Columbia; University of British Columbia; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Downscaling; Climate model; Orographic lift; Climate change; Computer science; Database; Precipitation; Climatology; Grid; Artificial neural network; Meteorology; Environmental science; Data mining; Remote sensing; Geography; Machine learning; Geology","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":[0.000488409,0.0004686098,0.0003110835,0.002685221,0.0003331329,0.000657653,0.0009225545,0.0004753708,0.006176676],"category_scores_gemma":[0.002409989,0.0002629599,0.0003952271,0.004790309,0.0001403051,0.0009892592,0.0006826444,0.0005855517,0.001769134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006772556,"about_ca_system_score_gemma":0.0009638256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0237258,"about_ca_topic_score_gemma":0.02698621,"domain_scores_codex":[0.9998114,0.00003332419,0.00002481359,0.0000584783,0.00004785805,0.00002412658],"domain_scores_gemma":[0.9993338,0.0001393715,0.00009713959,0.0001730759,0.0002107064,0.00004587087],"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":[0.0003651779,0.0003874116,0.09621023,0.0008962201,0.0004063722,0.001323712,0.0004162528,0.4596621,0.007599215,0.008665084,0.1411954,0.2828729],"study_design_scores_gemma":[0.0002050312,0.0001035202,0.109092,0.0004101097,0.0001755189,0.0004064478,0.0008315429,0.5953602,0.01790264,0.01171188,0.2636288,0.0001722584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2313646,0.001080773,0.05590412,0.0008222862,0.0002480622,0.000189117,0.6943062,0.005800293,0.01028451],"genre_scores_gemma":[0.4412996,0.001081248,0.08687888,0.00008813623,0.00006877429,0.0003964599,0.4671961,0.0003780823,0.002612635],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0237258,"threshold_uncertainty_score":0.04717541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03540132981286964,"score_gpt":0.2516837870842791,"score_spread":0.2162824572714095,"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."}}