{"id":"W3139945928","doi":"10.1175/jtech-d-20-0081.1","title":"Deep-learning-based precipitation observation quality control","year":2021,"lang":"en","type":"article","venue":"Journal of Atmospheric and Oceanic Technology","topic":"Precipitation Measurement and Analysis","field":"Earth and Planetary Sciences","cited_by":14,"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; Environment and Climate Change Canada; University Corporation for Atmospheric Research; Mitacs; BC Hydro; National Center for Atmospheric Research; National Science Foundation","keywords":"Computer science; Terrain; Convolutional neural network; Artificial intelligence; Classifier (UML); Artificial neural network; Precipitation; Pattern recognition (psychology); Machine learning; Remote sensing; Meteorology; Cartography; Geology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005610676,0.00008179541,0.0002319155,0.00002081358,0.00009934953,0.0000324163,0.0000971043,0.0001027873,0.0004680541],"category_scores_gemma":[0.0006436294,0.0000681648,0.00007465653,0.0004949052,0.00005561047,0.000177763,0.00000363085,0.0002096354,0.000007784629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008164794,"about_ca_system_score_gemma":0.00008822959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001077571,"about_ca_topic_score_gemma":0.00007489401,"domain_scores_codex":[0.9989703,0.0001513321,0.0004009058,0.0001185387,0.000231503,0.0001273623],"domain_scores_gemma":[0.9989246,0.0001512858,0.0004263047,0.00007791763,0.0003648176,0.00005507009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005015147,0.00002205454,0.8794219,0.00001312464,0.00006916613,0.00001320929,0.00005303319,0.01190146,0.0004245336,0.0001634066,0.0000531247,0.1078148],"study_design_scores_gemma":[0.001004865,0.0002479934,0.9184601,0.00002130204,0.00008768775,0.00002274307,0.0007253812,0.07537784,0.0002116828,0.002177092,0.001561932,0.000101386],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9159524,0.003886738,0.07765321,0.002095429,0.0001683172,0.00003973831,0.000001263626,0.00003203279,0.0001708981],"genre_scores_gemma":[0.9859335,0.0001881309,0.013524,0.0002258294,0.00004589388,1.839741e-7,0.000007512316,0.000002228704,0.00007273242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1077135,"threshold_uncertainty_score":0.5124865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01429295122774551,"score_gpt":0.2295671098827115,"score_spread":0.215274158654966,"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."}}