{"id":"W3108040709","doi":"10.3389/frwa.2020.536743","title":"Downscaling Satellite and Reanalysis Precipitation Products Using Attention-Based Deep Convolutional Neural Nets","year":2020,"lang":"en","type":"article","venue":"Frontiers in Water","topic":"Precipitation Measurement and Analysis","field":"Earth and Planetary Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Downscaling; Precipitation; Satellite; Environmental science; Baseline (sea); Predictability; Deep learning; Convolutional neural network; Artificial neural network; Computer science; Remote sensing; Meteorology; Artificial intelligence; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002994939,0.0001120777,0.0001715173,0.0001635105,0.0001131971,0.00007513228,0.00008016853,0.00004170562,0.0001919266],"category_scores_gemma":[0.00004357766,0.00008673799,0.0000533701,0.0003034762,0.00005595181,0.0002909928,0.000005692667,0.00008379573,0.00001973216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009721208,"about_ca_system_score_gemma":0.00001572771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001335453,"about_ca_topic_score_gemma":0.0001251323,"domain_scores_codex":[0.9988175,0.0001320426,0.000252568,0.0003059744,0.0002755327,0.0002163691],"domain_scores_gemma":[0.999689,0.00001931201,0.00005574931,0.00007676563,0.00007023256,0.00008891816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004813969,0.000005712753,0.8993618,0.00002137576,0.00003977884,0.000002725067,0.0004452125,0.09064692,0.001853769,8.328203e-7,0.00008000768,0.007493748],"study_design_scores_gemma":[0.0002807202,0.00001872641,0.2359334,0.000008740187,0.00006907231,3.855255e-7,0.0001642534,0.7625321,0.0004474253,0.0001155552,0.0003038701,0.0001257492],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9764296,0.001114123,0.01971123,0.002205343,0.000266406,0.0001346296,0.00001090998,0.00002622684,0.0001015751],"genre_scores_gemma":[0.9844404,0.00002096729,0.01453989,0.0003844802,0.00008890368,9.132537e-7,0.0004964027,0.000003301155,0.0000247689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6718852,"threshold_uncertainty_score":0.3537073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701064006665546,"score_gpt":0.2064155630728684,"score_spread":0.1794049230062129,"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."}}