{"id":"W1897501679","doi":"10.1029/2012jd017864","title":"Predictor selection for downscaling GCM data with LASSO","year":2012,"lang":"en","type":"article","venue":"Journal of Geophysical Research Atmospheres","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Downscaling; Collinearity; Lasso (programming language); Selection (genetic algorithm); Computer science; Regression; Elastic net regularization; Model selection; Climate model; Feature selection; Data mining; Climatology; Statistics; Climate change; Precipitation; Machine learning; Mathematics; Meteorology; Geology; Geography","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":[0.005575043,0.00133079,0.001316336,0.0008939779,0.0008428884,0.0008078111,0.001104532,0.0006659076,0.002327592],"category_scores_gemma":[0.01004048,0.0003751563,0.001035828,0.001211483,0.0004797456,0.0005280134,0.0008387431,0.001562596,0.0005338404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005744679,"about_ca_system_score_gemma":0.001798441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01688726,"about_ca_topic_score_gemma":0.01427453,"domain_scores_codex":[0.9983808,0.0009504078,0.00008174354,0.0002602595,0.0001976699,0.0001290629],"domain_scores_gemma":[0.99755,0.001409591,0.0002838651,0.0002041994,0.000492421,0.00005998198],"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":[0.0006302441,0.0001982179,0.024122,0.0003982785,0.0005133362,0.0003161828,0.0003743088,0.6959081,0.01067542,0.005992012,0.01270427,0.2481676],"study_design_scores_gemma":[0.00003275607,0.0000357759,0.003570831,0.00001846064,0.00001915584,0.00001474688,0.00004409505,0.9917151,0.001800244,0.00109404,0.001635826,0.00001897856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1282381,0.0005405019,0.8654938,0.0004428027,0.0001449762,0.0002660767,0.00132863,0.002132298,0.001412966],"genre_scores_gemma":[0.4339913,0.0002804552,0.5579197,0.0002261748,0.0001077949,0.0007587377,0.004805119,0.0004392831,0.001471505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01688726,"threshold_uncertainty_score":0.03357792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216786816871761,"score_gpt":0.3551937817183265,"score_spread":0.2335151000311503,"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."}}