{"id":"W4322492511","doi":"10.1080/14680629.2023.2182135","title":"Evaluating the use of machine learning for moisture content prediction in base and subgrade layers","year":2023,"lang":"en","type":"article","venue":"Road Materials and Pavement Design","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Subgrade; Water content; Moisture; Environmental science; Geotechnical engineering; Predictive modelling; Machine learning; Engineering; Computer science; Materials science; Composite material","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005470205,0.0000607202,0.0001034388,0.00002334113,0.00004966835,0.00003013204,0.0000210897,0.00002161395,0.000005763106],"category_scores_gemma":[0.00004464254,0.00004308464,0.00001067425,0.00006084627,0.00001150697,0.00003168322,0.00001228785,0.00002989284,5.547234e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005450479,"about_ca_system_score_gemma":0.00000210326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009793685,"about_ca_topic_score_gemma":0.000003116283,"domain_scores_codex":[0.9995476,0.00008185419,0.0001481659,0.00008240678,0.00005154129,0.00008844644],"domain_scores_gemma":[0.9996953,0.0001926888,0.00002768487,0.00005549826,0.00001175152,0.00001708964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001454791,0.000006671498,0.0003148507,0.00008278347,0.0000120589,1.272706e-7,0.0001712204,0.02352056,0.9698426,0.000213236,0.00004730009,0.005774057],"study_design_scores_gemma":[0.0009844676,0.0003478462,0.08084814,0.0001006556,0.00005791193,7.026067e-7,0.0001705488,0.7115929,0.2035546,0.001527177,0.0006605557,0.0001545009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819383,0.0000597677,0.0172459,0.00009039717,0.00005591033,0.0005261605,0.00004326192,0.00003885316,0.000001426213],"genre_scores_gemma":[0.9924956,0.0001185517,0.007055202,0.00001408958,0.00002687089,0.0002073776,0.00002443635,0.000009954776,0.0000479402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.766288,"threshold_uncertainty_score":0.1756941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2264217670998155,"score_gpt":0.325775546602016,"score_spread":0.09935377950220053,"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."}}