{"id":"W2937082058","doi":"10.5194/acp-20-2303-2020","title":"Technical note: Deep learning for creating surrogate models of precipitation in Earth system models","year":2020,"lang":"en","type":"article","venue":"Atmospheric chemistry and physics","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Pacific Northwest National Laboratory; Battelle; Laboratory Directed Research and Development; U.S. Department of Energy; Western Washington University; Division of Chemical, Bioengineering, Environmental, and Transport Systems; Nvidia; National Science Foundation","keywords":"Forcing (mathematics); Hyperparameter; Artificial neural network; Precipitation; Computer science; Sampling (signal processing); Earth system science; Convolutional neural network; Machine learning; Climatology; Environmental science; Meteorology; Artificial intelligence; Geology; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001008793,0.0000880792,0.0001781403,1.837892e-7,0.00007615167,0.00001470604,0.00006508904,0.00006241103,0.00006520183],"category_scores_gemma":[0.0000361516,0.00007897885,0.0000392628,0.0001406942,0.00003539173,0.0001459122,0.000007148335,0.0001095987,0.000001308306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003020424,"about_ca_system_score_gemma":0.00001382613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006262575,"about_ca_topic_score_gemma":0.000006963211,"domain_scores_codex":[0.9993612,0.00002595576,0.0002032783,0.0001865689,0.00009086917,0.0001321254],"domain_scores_gemma":[0.9994866,0.0002761311,0.000076141,0.00005676937,0.00003172781,0.00007262574],"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":[0.00004814954,0.000008251016,0.002795125,0.0001723244,0.000003065645,4.206939e-7,0.0004296203,0.9417765,0.001107781,0.0003340864,5.042465e-7,0.05332414],"study_design_scores_gemma":[0.0002673663,0.00006201064,0.001618277,0.00001883403,0.00001097255,4.579511e-7,0.0001700762,0.9927465,0.0002895088,0.00471403,0.0000157728,0.00008619666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6945301,0.0001933723,0.2944319,0.00002577618,0.000009749654,0.0001641625,0.00001349767,0.00003856111,0.01059292],"genre_scores_gemma":[0.9656852,0.00001460441,0.03410938,0.00001948668,0.00005809428,0.000003521918,0.00006413933,0.000002956665,0.00004254893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2711552,"threshold_uncertainty_score":0.3220664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02348356332026957,"score_gpt":0.2219178576626778,"score_spread":0.1984342943424082,"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."}}