{"id":"W2118370676","doi":"10.5194/npg-15-221-2008","title":"Robust nonlinear canonical correlation analysis: application to seasonal climate forecasting","year":2008,"lang":"en","type":"article","venue":"Nonlinear processes in geophysics","topic":"Climate variability and models","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Foundation for Climate and Atmospheric Sciences","keywords":"Mean squared error; Nonlinear system; Computer science; Artificial neural network; Statistics; Moment (physics); Canonical correlation; Mathematics; Climatology; Econometrics; Environmental science; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001638733,0.0001098907,0.0001560978,0.00004458132,0.0001092622,0.00001286612,0.0001492674,0.00006915293,0.000173724],"category_scores_gemma":[0.00009065844,0.0001113813,0.00004806173,0.001312248,0.00006351266,0.0001518755,0.0001200843,0.0001371497,0.0005055451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009739268,"about_ca_system_score_gemma":0.00005588221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001388297,"about_ca_topic_score_gemma":0.0003669517,"domain_scores_codex":[0.9989515,0.00001806132,0.0002225884,0.0003293136,0.000239725,0.0002387896],"domain_scores_gemma":[0.9995582,0.00007342741,0.00006664447,0.0001949399,0.00003326248,0.00007354641],"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":[0.00003485995,0.0003252499,0.1398809,0.00005770536,0.00001985132,0.000005375142,0.0005335042,0.8520582,0.0001057442,0.0001186427,0.00007123725,0.006788702],"study_design_scores_gemma":[0.0001285908,0.00002760015,0.0139942,0.00001231169,0.00004389605,0.000004186362,0.00001801832,0.9828959,0.0000654858,0.0001754607,0.002467638,0.0001667518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9538453,0.00001827692,0.03712954,0.0001027581,0.00006123725,0.0002954071,0.00006046534,0.00006562526,0.008421402],"genre_scores_gemma":[0.9681703,0.00003824457,0.03110507,0.0001753843,0.0001466576,0.00004309338,0.0001772553,0.00001635351,0.0001275741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1308376,"threshold_uncertainty_score":0.6497929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03301737925511579,"score_gpt":0.2520061547319014,"score_spread":0.2189887754767856,"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."}}