{"id":"W4210806187","doi":"10.3390/atmos13020255","title":"Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning","year":2022,"lang":"en","type":"article","venue":"Atmosphere","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Aeronautics and Space Administration","keywords":"Downscaling; Artificial neural network; Scale (ratio); Deep learning; Computer science; Transfer of learning; Artificial intelligence; Machine learning; Data mining; Remote sensing; Geology; Climate change; Cartography","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002080376,0.000309502,0.0002504952,4.092905e-7,0.001207717,0.0000692217,0.0006315242,0.00005565195,0.004080418],"category_scores_gemma":[0.000002757228,0.000257363,0.00003762663,0.0003377425,0.0002435363,0.0006610655,0.0005270285,0.0005486286,0.00003040357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001637719,"about_ca_system_score_gemma":0.00001694325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007056302,"about_ca_topic_score_gemma":0.001779648,"domain_scores_codex":[0.9975206,0.0001540921,0.0002759756,0.0008487095,0.0005841207,0.000616504],"domain_scores_gemma":[0.9990778,0.00003097186,0.00008235025,0.0006767787,0.000003210594,0.00012891],"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":[0.0001968893,0.00009961872,0.02135731,0.00000327945,0.00002045221,0.00002667973,0.001000986,0.9615285,0.003153476,0.00001029197,0.00007569884,0.01252682],"study_design_scores_gemma":[0.0006900026,0.0012494,0.001764887,0.00001285002,0.00007891509,0.00006446593,0.003802827,0.9887559,0.0004292476,0.00003766747,0.002424327,0.0006894586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8988246,0.00004781496,0.09942921,0.00008388326,0.00008458737,0.0002674187,0.000006828156,0.0001125446,0.001143061],"genre_scores_gemma":[0.8875764,0.000006977635,0.1109979,0.0003788025,0.0001550897,0.00005503026,0.0001311856,0.00007198668,0.0006266215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02722745,"threshold_uncertainty_score":0.9999878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398993990865247,"score_gpt":0.2137069314940739,"score_spread":0.1997169915854214,"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."}}