{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005060657,0.0002022397,0.0005231611,0.0001266547,0.00007566153,0.00002832604,0.0001142171,0.0001323072,0.000005167279],"category_scores_gemma":[0.0001760501,0.0001662202,0.0001065762,0.0001466922,0.00000154528,0.00009608095,0.00007409049,0.0005575002,7.815874e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005102732,"about_ca_system_score_gemma":0.00001842517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.77183e-7,"about_ca_topic_score_gemma":0.000001188253,"domain_scores_codex":[0.9987348,0.0000282196,0.0006546759,0.0001475182,0.0002055765,0.0002291703],"domain_scores_gemma":[0.9991992,0.0002082424,0.000172323,0.0001424183,0.0001473625,0.0001304148],"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":[0.00002769189,0.00004524831,0.000008566791,0.0002864282,0.0001353475,0.000004682354,0.00006841457,0.9489182,0.04561645,0.0006246227,0.00002624083,0.004238144],"study_design_scores_gemma":[0.0006429619,0.0003997486,0.00001132047,0.0002690674,0.0001523422,0.0001324402,0.0001089362,0.9544937,0.03941531,0.0002450506,0.003969564,0.0001595351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02262961,0.003557834,0.9731417,0.00003655186,0.0003889788,0.00009484325,0.00007501595,0.00007451042,9.08952e-7],"genre_scores_gemma":[0.9399546,0.0007138056,0.05910514,0.00000589632,0.0001043123,0.000006179731,0.0000582048,0.00004728634,0.000004560222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.917325,"threshold_uncertainty_score":0.6778263,"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."}}