{"id":"W4210556466","doi":"10.5194/gmd-2021-420","title":"A comparative analysis for deep learning model (hyDL-CO v1.0) and Kalman Filter to predict CO in China","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":1,"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; Convolutional neural network; Correlation; Deep learning; Data assimilation; Carbon monoxide; Artificial intelligence; Artificial neural network; Computer science; Environmental science; Statistics; Atmospheric sciences; Meteorology; Econometrics; Pattern recognition (psychology); Mathematics; Chemistry; Geology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001541341,0.0008636527,0.0004791734,0.000577336,0.0003534773,0.0006498927,0.0007444134,0.0007004891,0.0006751724],"category_scores_gemma":[0.001819117,0.0003574684,0.000770992,0.0004455094,0.0003186776,0.0009857632,0.0007218097,0.0005853465,0.0001740459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001611096,"about_ca_system_score_gemma":0.001794912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1721828,"about_ca_topic_score_gemma":0.09123465,"domain_scores_codex":[0.9996762,0.0000680618,0.00002182534,0.0001177297,0.00006472275,0.0000515004],"domain_scores_gemma":[0.999235,0.0002821399,0.00005335105,0.0000719833,0.0002995611,0.00005785643],"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":[0.0002166053,0.000113591,0.05643854,0.00009436615,0.000183837,0.00008089774,0.00004603497,0.9166437,0.002135047,0.0005179157,0.0009329584,0.02259647],"study_design_scores_gemma":[0.00001366559,0.00002766357,0.006139932,0.000004558154,0.00002404226,0.000003723224,0.00001109426,0.9925991,0.0009374304,0.00009598412,0.0001342743,0.000008599929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774712,0.0005409914,0.01773096,0.0004054401,0.0000600147,0.00002585159,0.0006933396,0.0006453721,0.002426812],"genre_scores_gemma":[0.9959391,0.00008710634,0.002841423,0.00003598418,0.000007588443,0.00001248345,0.0006746309,0.0000243092,0.000377328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1721828,"threshold_uncertainty_score":0.3423612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531938883825236,"score_gpt":0.2612146759547265,"score_spread":0.2458952871164741,"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."}}