{"id":"W4408435786","doi":"10.5194/egusphere-egu25-8355","title":"Bridging the Fleet Distribution Data Gap with Satellite Imagery and Deep Learning for GHG Estimation","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Vehicle License Plate Recognition","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Bridging (networking); Satellite imagery; Satellite; Deep learning; Remote sensing; Greenhouse gas; Environmental science; Distribution (mathematics); Satellite image; Estimation; Computer science; Meteorology; Geography; Artificial intelligence; Oceanography; Engineering; Geology; Aerospace engineering; Mathematics; Systems engineering","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":[0.0003818284,0.0002291709,0.0002092573,0.00005751152,0.0001379671,0.0002386024,0.0001981999,0.0001520634,0.000006836215],"category_scores_gemma":[0.0001032762,0.0001809002,0.00002946348,0.00009601588,0.00003178018,0.0002436325,0.0002932499,0.0004930553,0.000005515862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007760412,"about_ca_system_score_gemma":0.00002427601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003425556,"about_ca_topic_score_gemma":0.00004485824,"domain_scores_codex":[0.999015,0.00003767743,0.000232837,0.0003725543,0.000122617,0.0002193391],"domain_scores_gemma":[0.9991156,0.0002568683,0.00007328541,0.0004488994,0.00006926181,0.00003604608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002908901,0.000007140269,0.0002460351,0.001216655,0.0001500897,0.000002043609,0.0001480959,0.2651621,0.0001245878,0.000129097,0.000308464,0.7324766],"study_design_scores_gemma":[0.0001883877,0.000008767933,0.001235755,0.0003607085,0.0001516768,0.00001347122,0.00005584673,0.9953938,0.0005395186,0.000342931,0.00148176,0.0002274096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02437724,0.001088202,0.9712503,0.0002167012,0.0001849189,0.0007040515,0.0003356898,0.0005156017,0.001327267],"genre_scores_gemma":[0.9563019,0.001469444,0.02144145,0.000034852,0.0001938314,0.000140537,0.02018934,0.00005202402,0.0001766547],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9498089,"threshold_uncertainty_score":0.7376896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620416819836451,"score_gpt":0.2550309095867798,"score_spread":0.2288267413884152,"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."}}