{"id":"W3174650221","doi":"10.1016/j.jag.2021.102404","title":"Reconstructing GRACE-like TWS anomalies for the Canadian landmass using deep learning and land surface model","year":2021,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Geophysics and Gravity Measurements","field":"Earth and Planetary Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Waterloo","funders":"Natural Resources Canada","keywords":"Forcing (mathematics); Earth system science; Deep learning; Water cycle; Meteorology; Scale (ratio); Climate model; Data assimilation; Satellite; Climate change; Climatology; Computer science; Environmental science; Geography; Artificial intelligence; Geology; Engineering; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002479235,0.0009973006,0.0003114322,0.001330534,0.0008890858,0.0007210204,0.001298509,0.0007307818,0.001470439],"category_scores_gemma":[0.0008123774,0.0003919084,0.0007104422,0.00194061,0.0004680055,0.0006775587,0.000607488,0.0009475788,0.0003930752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01010075,"about_ca_system_score_gemma":0.01027848,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9455689,"about_ca_topic_score_gemma":0.9519498,"domain_scores_codex":[0.9998472,0.000006018628,0.000004101288,0.00003331785,0.0000600079,0.00004946916],"domain_scores_gemma":[0.999806,0.00001637761,0.0000198651,0.00001694529,0.0001107846,0.00002993585],"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":[0.000170521,0.0001418264,0.04840505,0.00006930503,0.0001596802,0.0003291162,0.00008483254,0.8183718,0.005335703,0.003577077,0.01198301,0.111372],"study_design_scores_gemma":[0.00001059054,0.000005128893,0.0103872,0.000004292074,0.00001408693,0.000009997909,0.00003092119,0.9869834,0.0009100462,0.0004853376,0.001139968,0.00001904674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9236594,0.001216567,0.04923286,0.001999289,0.0001244008,0.0001047084,0.0121432,0.002743675,0.008775884],"genre_scores_gemma":[0.9703531,0.0003724315,0.01650221,0.00008970959,0.00001347651,0.00002530737,0.009215676,0.000109682,0.003318358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05443108,"threshold_uncertainty_score":0.1095032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03565958882697706,"score_gpt":0.23159662678267,"score_spread":0.1959370379556929,"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."}}