{"id":"W3187636822","doi":"10.1139/cjce-2020-0613","title":"Winter road surface condition classification using convolutional neural network (CNN): visible light and thermal image fusion","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Convolutional neural network; Road surface; Environmental science; Thermal; Snow removal; Snow; Computer science; Meteorology; Remote sensing; Artificial intelligence; Engineering; Geology; Civil engineering; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000179808,0.00009381253,0.0001176072,0.00004565514,0.0001125249,0.00007990926,0.00006441215,0.00005357431,0.001235113],"category_scores_gemma":[0.00003299781,0.0001002065,0.00003996246,0.0001335476,0.00004521607,0.0004419262,0.00002051298,0.0001188385,0.00001111507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002672974,"about_ca_system_score_gemma":0.00009524162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003837357,"about_ca_topic_score_gemma":0.01051157,"domain_scores_codex":[0.9992781,0.0000326483,0.0002318459,0.0001117473,0.0001289028,0.0002167311],"domain_scores_gemma":[0.9995351,0.00001387457,0.0001068477,0.00007760152,0.00003691216,0.0002296322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000006011712,0.000002948189,0.05267997,0.00000860528,0.00001345456,0.00005985465,0.00008066202,0.2279302,0.718408,0.000044431,0.0006024906,0.0001632935],"study_design_scores_gemma":[0.000462254,0.00003878701,0.8212472,0.0001374725,0.00004413875,0.001418104,0.00008766416,0.1626749,0.01046512,0.00008766346,0.003072694,0.0002639804],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962461,0.0002174771,0.001947597,0.0002010894,0.001026664,0.00004010473,0.000004405432,0.000007569276,0.0003089927],"genre_scores_gemma":[0.9985093,0.000006504659,0.001178425,0.0000329262,0.0002421053,3.590152e-7,0.000004842835,0.00001353974,0.00001194061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7685672,"threshold_uncertainty_score":0.9996779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007974371526258349,"score_gpt":0.1893239927666827,"score_spread":0.1813496212404243,"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."}}