{"id":"W3105660549","doi":"10.1175/jamc-d-20-0057.1","title":"Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part I: Daily Maximum and Minimum 2-m Temperature","year":2020,"lang":"en","type":"article","venue":"Journal of Applied Meteorology and Climatology","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Hydro (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; University Corporation for Atmospheric Research; Mitacs; BC Hydro; National Center for Atmospheric Research; National Science Foundation","keywords":"Downscaling; Elevation (ballistics); Autoencoder; Computer science; Climatology; Environmental science; Deep learning; Artificial intelligence; Meteorology; Mathematics; Geology; Geography","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":[0.0005689036,0.0001714317,0.0007642555,0.00004745873,0.0001333659,0.00001378006,0.0001464926,0.0002461526,0.0004685383],"category_scores_gemma":[0.0001641183,0.0001281933,0.00006277195,0.0002241778,0.0003656645,0.00005314196,0.0000315941,0.0004808357,0.000001947847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000233283,"about_ca_system_score_gemma":0.00003570564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002656085,"about_ca_topic_score_gemma":0.0001765394,"domain_scores_codex":[0.9985054,0.0001847544,0.0006489518,0.00024183,0.000118611,0.0003004619],"domain_scores_gemma":[0.998472,0.0008616601,0.0003941324,0.00006944217,0.0000611716,0.0001415434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002989531,0.0000870926,0.9452924,0.0001377089,0.0002208703,0.0001156779,0.001650259,0.03959389,0.005516039,0.001024445,0.0005117143,0.002860382],"study_design_scores_gemma":[0.004932066,0.002402959,0.9349614,0.00002195635,0.0002529117,0.0002588703,0.00540065,0.036911,0.0002783305,0.003692016,0.01049883,0.0003890188],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934953,0.002108117,0.0002282477,0.003617419,0.0001022092,0.0001075912,0.00001168474,0.000009411633,0.0003200104],"genre_scores_gemma":[0.9915267,0.0005460543,0.005959545,0.001884321,0.00005438794,8.214894e-7,0.00002305715,0.000003887782,0.000001222054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.010331,"threshold_uncertainty_score":0.522757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02140605386327046,"score_gpt":0.222555566859836,"score_spread":0.2011495129965655,"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."}}