{"id":"W4280535937","doi":"10.5194/acp-2022-251","title":"Inverse modeling of Chinese NO <sub>x</sub> emissions using deep learning: Integrating in situ observations with a satellite-based chemical reanalysis","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Government of Canada; National Aeronautics and Space Administration; California Institute of Technology; Jet Propulsion Laboratory","keywords":"NOx; Emission inventory; Environmental science; Atmospheric sciences; Satellite; In situ; Christian ministry; Nitrogen dioxide; Meteorology; Climatology; Chemistry; Air quality index; Geography; Physics; Combustion; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004875543,0.0008700846,0.0004361032,0.00033328,0.0003190381,0.0005286116,0.0009046605,0.0005239082,0.0006935612],"category_scores_gemma":[0.000763221,0.0004139553,0.0008792703,0.0004766358,0.0003480666,0.0005481267,0.0006060787,0.0008062249,0.0001404861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008800103,"about_ca_system_score_gemma":0.001426626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07668907,"about_ca_topic_score_gemma":0.05550808,"domain_scores_codex":[0.9998685,0.00002126138,0.000007267335,0.00004963141,0.00002548122,0.00002783263],"domain_scores_gemma":[0.9998432,0.0000513956,0.00002077566,0.00001166721,0.00005719105,0.00001566291],"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":[0.00004278397,0.00006656374,0.01163972,0.00002914195,0.00009045186,0.00006651672,0.00002976307,0.9666477,0.002082407,0.0005893527,0.0005825243,0.01813305],"study_design_scores_gemma":[0.000002626776,0.00000359417,0.0007355436,0.000001060643,0.000005268536,0.000001209164,0.000002913019,0.9988146,0.000234752,0.0001308731,0.00006563028,0.00000203898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8529561,0.0007450068,0.1390744,0.0008671828,0.000169205,0.00004424081,0.0007826361,0.0008790917,0.004482145],"genre_scores_gemma":[0.9870947,0.000122711,0.01086478,0.00007116891,0.00002400844,0.00002458716,0.0005188565,0.00001960328,0.001259688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07668907,"threshold_uncertainty_score":0.1524854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0495589693397079,"score_gpt":0.2746858753285465,"score_spread":0.2251269059888386,"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."}}