{"id":"W3201279417","doi":"10.1016/j.conbuildmat.2021.124905","title":"Climate change impact on infrastructure: A machine learning solution for predicting pavement condition index","year":2021,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Climate change; Random forest; Naive Bayes classifier; Environmental science; Machine learning; Computer science; Storm surge; Support vector machine; Artificial intelligence; Storm; Meteorology; Geography; Ecology","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":[0.0001816217,0.0002091185,0.0002380572,0.0001069898,0.0002549524,0.0001462515,0.0000368266,0.0001178279,0.00009302346],"category_scores_gemma":[0.00004206981,0.0001905913,0.00005225,0.0000875057,0.00003857708,0.0002004663,0.00003473693,0.0001321081,0.000001342404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001172141,"about_ca_system_score_gemma":0.00001138935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009823701,"about_ca_topic_score_gemma":0.000001495136,"domain_scores_codex":[0.9990351,0.00003517477,0.0002688802,0.0002226367,0.0001041025,0.0003340819],"domain_scores_gemma":[0.9996443,0.00003434627,0.00009206691,0.00009557222,0.00007130653,0.00006235566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006438074,0.00000471871,0.01196544,0.000259711,0.00005820316,0.000004113682,0.0001765021,0.003047767,0.9255444,0.001688141,0.00005586245,0.05713079],"study_design_scores_gemma":[0.001252472,0.0001190475,0.02264114,0.0004426902,0.00005572389,0.0001946455,0.000193712,0.01682055,0.9549949,0.001377546,0.001530334,0.0003772018],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9816838,0.0001179353,0.01464501,0.00003015626,0.002789786,0.0002684448,0.0001386765,0.000260118,0.00006607374],"genre_scores_gemma":[0.9947348,0.0002650478,0.003871881,0.00003930362,0.0008636836,0.0000706671,0.0001179712,0.00003358531,0.000003100289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05675359,"threshold_uncertainty_score":0.7772089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00979085035847268,"score_gpt":0.2497250692945557,"score_spread":0.239934218936083,"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."}}