{"id":"W3171829021","doi":"","title":"PMNet: Improving Aerosol Predictions using Deep Neural Nets for Limited Ground Stations","year":2020,"lang":"en","type":"article","venue":"100th American Meteorological Society Annual Meeting","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Aerosol; Environmental science; Meteorology; Artificial neural network; Computer science; Remote sensing; Artificial intelligence; 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":[0.0005080766,0.001195901,0.0008991855,0.0005198853,0.000343097,0.0007327135,0.001705691,0.001111009,0.003747727],"category_scores_gemma":[0.001338965,0.0005258402,0.0007235611,0.000529148,0.0001978576,0.001158573,0.0009784135,0.001363829,0.001264888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000480578,"about_ca_system_score_gemma":0.0008658437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02028928,"about_ca_topic_score_gemma":0.02865978,"domain_scores_codex":[0.9998553,0.00002002997,0.000006449479,0.00004821299,0.00004457743,0.00002539226],"domain_scores_gemma":[0.9997168,0.0001073641,0.00001921963,0.00004753821,0.00007866324,0.00003039479],"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":[0.0006270849,0.0004318809,0.005516047,0.0001363532,0.0004292662,0.0002467244,0.00002589671,0.7619864,0.004666806,0.001043031,0.02804456,0.196846],"study_design_scores_gemma":[0.00002275551,0.00001653222,0.0002242494,0.000002633544,0.00000794245,0.000004725975,0.000002246098,0.9983985,0.0006196002,0.0003494205,0.0003481175,0.000003351723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4818875,0.003267423,0.4368005,0.00149755,0.002418498,0.00026182,0.0141578,0.04918697,0.0105219],"genre_scores_gemma":[0.8084224,0.0004241909,0.1626359,0.0005372718,0.0003984848,0.0001358652,0.01503282,0.0009399651,0.0114731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02028928,"threshold_uncertainty_score":0.04034233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04191484468141522,"score_gpt":0.2764202714132212,"score_spread":0.234505426731806,"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."}}