{"id":"W3210739237","doi":"10.1016/j.jrmge.2021.08.006","title":"Comparison of machine learning methods for ground settlement prediction with different tunneling datasets","year":2021,"lang":"en","type":"article","venue":"Journal of Rock Mechanics and Geotechnical Engineering","topic":"Tunneling and Rock Mechanics","field":"Engineering","cited_by":153,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Hyperparameter optimization; Hyperparameter; Mean squared error; Particle swarm optimization; Artificial neural network; Support vector machine; Random forest; Correlation coefficient; Artificial intelligence; Computer science; Mean absolute error; Sensitivity (control systems); Machine learning; Data mining; Cross-validation; Reliability (semiconductor); Statistics; Mathematics; Engineering","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":[0.005555436,0.002504712,0.00136695,0.003430657,0.0006039224,0.001182474,0.001587879,0.001369916,0.0007554175],"category_scores_gemma":[0.008565212,0.0002903911,0.001714642,0.002676199,0.0005277746,0.00135031,0.001000937,0.00120996,0.0003816354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006989634,"about_ca_system_score_gemma":0.001005211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008733855,"about_ca_topic_score_gemma":0.006115792,"domain_scores_codex":[0.9977002,0.0008550194,0.0002965663,0.0005298005,0.0004508471,0.0001675019],"domain_scores_gemma":[0.9952003,0.002849187,0.0003534288,0.0005337285,0.000953682,0.0001096496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003435432,0.0004456386,0.03395056,0.0003960687,0.0005856967,0.0001625382,0.00009759387,0.7570829,0.001865864,0.000809478,0.003172072,0.201088],"study_design_scores_gemma":[0.00001274504,0.00008117948,0.004251262,0.00002485579,0.00003607519,0.00002576307,0.00005347424,0.9940128,0.0007896028,0.0004014627,0.0002959236,0.00001491367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7248204,0.004699587,0.2587511,0.0005607901,0.0004126152,0.0002792203,0.002738538,0.00369625,0.004041553],"genre_scores_gemma":[0.920331,0.0008005225,0.07201322,0.0001240067,0.00007884839,0.0002440687,0.005472777,0.0001022115,0.0008333513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008733855,"threshold_uncertainty_score":0.02938032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646997854747846,"score_gpt":0.281709847990445,"score_spread":0.2652398694429666,"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."}}