{"id":"W2771326676","doi":"10.1109/icdmw.2017.49","title":"A Machine Learning Approach to Non-uniform Spatial Downscaling of Climate Variables","year":2017,"lang":"en","type":"article","venue":"","topic":"Climate variability and models","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Downscaling; Context (archaeology); Artificial neural network; Mean squared error; Computer science; Extreme learning machine; Linear regression; Term (time); Artificial intelligence; Machine learning; Climatology; Meteorology; Statistics; Mathematics; Geography; Precipitation; Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001164535,0.0007200887,0.0007125098,0.0006771975,0.0004983753,0.0006090307,0.001192062,0.000721755,0.001142572],"category_scores_gemma":[0.003863894,0.0003780379,0.0009640855,0.0009624248,0.0005124022,0.0009429421,0.001052553,0.001514497,0.0002742431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005838725,"about_ca_system_score_gemma":0.0009832844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007977154,"about_ca_topic_score_gemma":0.01055318,"domain_scores_codex":[0.9995339,0.0001038558,0.00003874646,0.0001705459,0.000115221,0.00003781253],"domain_scores_gemma":[0.9990438,0.0003070962,0.0001821471,0.0002111044,0.0002298391,0.00002608886],"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":[0.00005386343,0.00007139114,0.002193724,0.00007498929,0.0001895785,0.0001079679,0.0001085717,0.7360547,0.0118594,0.009910862,0.001790324,0.2375847],"study_design_scores_gemma":[0.000005758596,0.00001320953,0.0006122033,0.000005280299,0.000009741194,0.00001949037,0.00001046374,0.9929749,0.001752833,0.003760493,0.000827346,0.000008391486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.013015,0.0001379425,0.9855055,0.0001222252,0.00004339221,0.00002410405,0.00006946154,0.0004953207,0.0005870987],"genre_scores_gemma":[0.2989413,0.0002213738,0.6981987,0.000170066,0.0001760431,0.0001218318,0.0003236243,0.0001743685,0.001672552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007977154,"threshold_uncertainty_score":0.01586145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02011171604799009,"score_gpt":0.2451188365116872,"score_spread":0.2250071204636971,"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."}}