{"id":"W4301396626","doi":"10.1002/geot.202200047","title":"Practical recommendations for machine learning in underground rock engineering – On algorithm development, data balancing, and input variable selection","year":2022,"lang":"en","type":"article","venue":"Geomechanics and Tunnelling","topic":"Dam Engineering and Safety","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Toolbox; Machine learning; Computer science; Algorithm; Process (computing); Artificial intelligence; Resource (disambiguation); Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06074925,0.001739671,0.001235924,0.002971465,0.001172099,0.006399168,0.004302541,0.004711786,0.01215814],"category_scores_gemma":[0.1758053,0.0009004865,0.001112979,0.002602731,0.003393395,0.01091315,0.003587437,0.007647162,0.007812025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002184039,"about_ca_system_score_gemma":0.005585884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002612028,"about_ca_topic_score_gemma":0.00444675,"domain_scores_codex":[0.9575899,0.03294717,0.002020922,0.00173462,0.005141157,0.0005662245],"domain_scores_gemma":[0.8249417,0.1299825,0.0042121,0.01241729,0.0254259,0.003020396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002973406,0.000740701,0.003825961,0.001112211,0.00008896083,0.0002209125,0.0006947328,0.04108036,0.002156142,0.1453808,0.1332442,0.6711577],"study_design_scores_gemma":[0.0003449002,0.0005252994,0.002110772,0.003931644,0.00005366384,0.0002447801,0.001681157,0.2621761,0.007610117,0.4316941,0.2894192,0.0002083128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004627862,0.003733032,0.8974649,0.082612,0.001218044,0.0006004995,0.0001701189,0.002369689,0.007203853],"genre_scores_gemma":[0.02794845,0.002193281,0.960327,0.004137815,0.0008991609,0.0007449267,0.0003634841,0.0003963909,0.002989454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06074925,"threshold_uncertainty_score":0.3212765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02771238770067212,"score_gpt":0.2427019547295757,"score_spread":0.2149895670289036,"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."}}