{"id":"W4392601196","doi":"10.5194/egusphere-egu24-7133","title":"The capability of deep learning model to predict atmospheric compositions across spatial and temporal domains","year":2024,"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":"","keywords":"Deep learning; Computer science; Environmental science; Artificial intelligence","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":[0.0007667364,0.000187698,0.0002113129,0.00000309827,0.0004627537,0.0001034006,0.0002473329,0.0001301642,0.00003998087],"category_scores_gemma":[0.00007507621,0.0001362273,0.00008945812,0.00009753084,0.0004084487,0.00003090456,0.002745667,0.0006197783,0.00002452793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001730645,"about_ca_system_score_gemma":0.0000154452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00518124,"about_ca_topic_score_gemma":0.001052191,"domain_scores_codex":[0.9984802,0.0000977384,0.0003574927,0.0004616344,0.0003191487,0.000283801],"domain_scores_gemma":[0.9992868,0.000145055,0.0001043127,0.0003266143,0.00001253556,0.0001247184],"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":[0.00003286271,0.00005109376,0.1473645,0.0001316287,0.00003842587,0.000001879545,0.007568974,0.7980818,0.0004642181,0.00008966678,0.0001100799,0.04606492],"study_design_scores_gemma":[0.00007133534,0.00007055089,0.02748252,0.00006697913,0.00002590626,0.000002589981,0.0008076875,0.9666984,0.0001446138,0.004262063,0.0001755821,0.0001917766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9218974,0.00006362906,0.07481226,0.000271673,0.0002431928,0.0002964921,0.00003408422,0.00009700446,0.002284323],"genre_scores_gemma":[0.9822339,0.00001019051,0.01692512,0.00001332033,0.00007795778,0.00004025192,0.000009123057,0.00001823261,0.0006719485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1686166,"threshold_uncertainty_score":0.7832521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01995492742436102,"score_gpt":0.284184104696463,"score_spread":0.264229177272102,"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."}}