{"id":"W4415568553","doi":"10.1080/15481603.2025.2571244","title":"Optimizing GAIN model to improve AOD imputation using MODIS MAIAC data and multi-source data fusion as an example","year":2025,"lang":"en","type":"article","venue":"GIScience & Remote Sensing","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Goddard Space Flight Center; National Science Foundation","keywords":"Missing data; Imputation (statistics); Moderate-resolution imaging spectroradiometer; Mean squared error; Leverage (statistics); Data modeling; Data quality","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008057909,0.0002389734,0.0001910305,0.00002705161,0.0006398386,0.0001856808,0.0009124344,0.00008671392,0.00001007548],"category_scores_gemma":[0.00008212635,0.0002389995,0.0000180297,0.0004468799,0.0003691131,0.001368111,0.004547094,0.0001607361,0.00001423682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003012251,"about_ca_system_score_gemma":0.00004146752,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01045675,"about_ca_topic_score_gemma":0.0004919057,"domain_scores_codex":[0.9973105,0.00006422541,0.0002887499,0.001429873,0.0004041593,0.0005025057],"domain_scores_gemma":[0.9979705,0.00003575789,0.0001092658,0.001645991,0.000006598129,0.0002319388],"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":[0.00000910736,0.00001450101,0.0001152691,0.000003447419,0.000001673663,0.000003316784,0.0008065481,0.5982191,0.07061981,0.000002229571,0.00001053171,0.3301944],"study_design_scores_gemma":[0.0002216042,0.00003097727,0.0003370072,0.00003972097,0.00002751836,0.00002079392,0.001364569,0.9968242,0.0003766362,0.0002955599,0.0001905337,0.0002708807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.451107,0.00001341227,0.5483433,0.00006961922,0.00006635738,0.0001818645,0.000008629549,0.00003338867,0.000176499],"genre_scores_gemma":[0.3860739,0.00001564068,0.6131111,0.0004666327,0.0000135863,5.317838e-8,0.00003802584,0.00001640241,0.0002646292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3986051,"threshold_uncertainty_score":0.9961327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0529087944506252,"score_gpt":0.2960191450565444,"score_spread":0.2431103506059192,"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."}}