{"id":"W4323314757","doi":"10.1080/10298436.2023.2183401","title":"Automated pothole condition assessment in pavement using photogrammetry-assisted convolutional neural network","year":2023,"lang":"en","type":"article","venue":"International Journal of Pavement Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Mitacs","keywords":"Pothole (geology); Photogrammetry; Convolutional neural network; Artificial neural network; Environmental science; Computer science; Civil engineering; Engineering; Artificial intelligence; Remote sensing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002261795,0.0008313955,0.0004825907,0.001085086,0.0001735572,0.0006243665,0.000962076,0.0007013565,0.001125119],"category_scores_gemma":[0.0006493612,0.0003291561,0.0005451865,0.0006461811,0.0002398679,0.0007502718,0.0005676023,0.0005148086,0.0004905975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000791231,"about_ca_system_score_gemma":0.000584605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01542913,"about_ca_topic_score_gemma":0.023452,"domain_scores_codex":[0.9997864,0.00001375145,0.00000851219,0.0000946223,0.00005259879,0.00004423386],"domain_scores_gemma":[0.9998159,0.00004118587,0.00003110765,0.0000325195,0.00006635166,0.00001296851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003639498,0.0002706307,0.01295703,0.0001722135,0.0001531601,0.0002709904,0.00006966721,0.4884716,0.05077425,0.000726666,0.003702614,0.4420672],"study_design_scores_gemma":[0.000003656941,0.00002931459,0.003884004,0.0000064879,0.00001654471,0.0000400804,0.0000102554,0.9893411,0.005995553,0.0002942891,0.0003704985,0.00000825818],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4602502,0.001105537,0.5242484,0.0002332656,0.0001252371,0.0001290005,0.001498658,0.008321557,0.004088071],"genre_scores_gemma":[0.9479379,0.0002958053,0.04773838,0.00005355526,0.00001844044,0.00003641492,0.001526295,0.00005061293,0.002342536],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01542913,"threshold_uncertainty_score":0.03067869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01349117070303713,"score_gpt":0.2846974993389563,"score_spread":0.2712063286359192,"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."}}