{"id":"W3200909181","doi":"10.1080/07038992.2021.1954498","title":"Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Geophysics and Gravity Measurements","field":"Earth and Planetary Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Waterloo","funders":"Natural Resources Canada","keywords":"Downscaling; Convolutional neural network; Data assimilation; Image resolution; Mean squared error; Remote sensing; Scale (ratio); Pixel; Residual; Computer science; Environmental science; Meteorology; Artificial intelligence; Geography; Algorithm; Mathematics; Cartography; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0004237959,0.0001364634,0.0002760103,0.0001357476,0.0002242836,0.00008098603,0.0001090675,0.000048778,0.00002600228],"category_scores_gemma":[0.0001482391,0.0001170651,0.00006864089,0.0001865229,0.00002978877,0.0001155104,0.000007532826,0.0002885635,0.000001216418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007206476,"about_ca_system_score_gemma":0.002667859,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9130219,"about_ca_topic_score_gemma":0.9819555,"domain_scores_codex":[0.9985358,0.0001010641,0.0003505481,0.000183112,0.000406928,0.000422602],"domain_scores_gemma":[0.9989809,0.00001849969,0.0001732328,0.0001322457,0.0001866754,0.0005084476],"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":[0.00002986625,0.000002056964,0.005514556,0.00002371104,0.00004604494,0.0003986361,0.0009211065,0.8756157,0.002893021,6.213843e-7,0.00003468432,0.11452],"study_design_scores_gemma":[0.0003401657,0.00004647297,0.009208796,0.0001508355,0.00005795957,0.0001778787,0.0003540193,0.9799641,0.008178988,0.0001539891,0.001137749,0.0002290507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830598,0.0001571747,0.01541214,0.0003438084,0.0008248054,0.00006827366,0.000008919714,0.000001648627,0.000123404],"genre_scores_gemma":[0.976003,0.000001324772,0.02352679,0.00008375537,0.0003244749,1.285964e-9,0.00001695027,0.0000073687,0.00003632611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.114291,"threshold_uncertainty_score":0.4773778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06613539914611033,"score_gpt":0.2004358523531546,"score_spread":0.1343004532070443,"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."}}