{"id":"W3136123911","doi":"10.1016/j.powtec.2021.04.026","title":"Characterizing soot in TEM images using a convolutional neural network","year":2021,"lang":"en","type":"preprint","venue":"Powder Technology","topic":"Oil, Gas, and Environmental Issues","field":"Energy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Allianz Industrie Forschung","keywords":"Soot; Convolutional neural network; Aggregate (composite); Particle size; Particle (ecology); Range (aeronautics); Characterization (materials science); Transmission electron microscopy; Artificial neural network; Biological system; Materials science; Computer science; Pattern recognition (psychology); Artificial intelligence; Nanotechnology; Chemistry; Chemical engineering; Composite material; Combustion; Engineering; Geology","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0001246155,0.0003968208,0.0006302861,0.0003179663,0.0001022316,0.00006820308,0.0004314346,0.0009322484,0.0003350012],"category_scores_gemma":[0.00003753155,0.0004543721,0.0001355816,0.0002764578,0.0003351561,0.0001063314,0.001491268,0.0011763,0.00004520963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002827553,"about_ca_system_score_gemma":0.00005065776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001324395,"about_ca_topic_score_gemma":0.000466551,"domain_scores_codex":[0.9978226,0.00008840242,0.0004709086,0.0007551927,0.0001785345,0.0006843227],"domain_scores_gemma":[0.9990918,0.00003555478,0.0002032387,0.0005946601,0.00002255532,0.00005216573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001751768,0.001091025,0.4101987,0.0008680574,0.0009174229,0.002644873,0.002143542,0.1258238,0.3749101,0.01620325,0.0009804277,0.06404365],"study_design_scores_gemma":[0.006896126,0.0004791377,0.5214891,0.005211416,0.0008319248,0.002207703,0.01008811,0.0769605,0.1561781,0.1285305,0.08048042,0.01064694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903872,0.005068456,0.0001062171,0.001608882,0.001159873,0.0001687539,0.00001582393,0.0003571546,0.001127645],"genre_scores_gemma":[0.9941767,0.0003222977,0.004242065,0.0002792323,0.0004340603,0.00006804023,0.0001782684,0.00007092845,0.0002283848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2187319,"threshold_uncertainty_score":0.9997908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02306582683692727,"score_gpt":0.2521895522888742,"score_spread":0.2291237254519469,"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."}}