{"id":"W4281674072","doi":"10.5194/gmd-15-4225-2022","title":"A comparative analysis for a deep learning model (hyDL-CO v1.0) and Kalman filter to predict CO concentrations in China","year":2022,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Science and Technology of China; National Natural Science Foundation of China","keywords":"Kalman filter; Data assimilation; Convolutional neural network; Correlation; Environmental science; Artificial neural network; Deep learning; Meteorology; Computer science; Statistics; Atmospheric sciences; Artificial intelligence; Mathematics; Climatology; Geology; Physics","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":[0.0005209618,0.0002116546,0.000281681,0.00006469137,0.0009176622,0.00006200255,0.0002592815,0.00003619679,0.0004824843],"category_scores_gemma":[0.000007200364,0.000223637,0.00006631877,0.0006213387,0.0001582832,0.0001543011,0.0003981791,0.0001793468,0.00002412118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007121972,"about_ca_system_score_gemma":0.00004231217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009140844,"about_ca_topic_score_gemma":0.0003162096,"domain_scores_codex":[0.9978254,0.00005608315,0.0003761266,0.0007446377,0.0005151134,0.0004825977],"domain_scores_gemma":[0.9994791,0.00002181335,0.00009563751,0.0002066179,0.000004666493,0.0001922087],"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":[0.00002870292,0.0001181101,0.06714954,0.000003460231,0.00003847344,0.000001283034,0.01314054,0.9174935,0.0004706103,0.00003726569,0.0003647502,0.001153721],"study_design_scores_gemma":[0.0003268809,0.00003601637,0.07927548,0.000002348955,0.00003387191,0.00000136126,0.0008352025,0.9159077,0.0000577494,0.0001325244,0.003138658,0.0002521478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5417918,0.000008952422,0.4568062,0.00004680909,0.00003034523,0.00044416,0.00003419684,0.00001828205,0.0008193158],"genre_scores_gemma":[0.8868366,0.000004454582,0.1048659,0.0001608518,0.000002937817,0.0005516355,0.0002255982,0.00001171841,0.007340271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3519402,"threshold_uncertainty_score":0.9119654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01622132626637988,"score_gpt":0.2367477500764866,"score_spread":0.2205264238101067,"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."}}