{"id":"W4411450778","doi":"10.21203/rs.3.rs-6649664/v1","title":"Enhanced Prediction of Persistent Earthquake-Induced Groundwater Level Changes with Advanced Feature Engineering and Machine Learning","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Interpretability; Feature selection; Hydrogeology; Groundwater; Feature (linguistics); Machine learning; Random forest; Probabilistic logic; Computer science; Bayesian probability; Support vector machine; Data mining; Artificial intelligence; Geology; Geotechnical engineering","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":[0.0003999271,0.0003812827,0.0005910086,0.0003910953,0.0001314841,0.0004468019,0.0004144103,0.0005275903,0.0005734971],"category_scores_gemma":[0.001630473,0.0002132396,0.0003985589,0.0003627467,0.000146564,0.0006124373,0.0004509088,0.0006099423,0.0001662787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002180877,"about_ca_system_score_gemma":0.000365402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003750008,"about_ca_topic_score_gemma":0.004262165,"domain_scores_codex":[0.9998866,0.0000253919,0.000008198617,0.00003680938,0.00002214408,0.00002072015],"domain_scores_gemma":[0.9992913,0.0004510763,0.00005780057,0.0000549406,0.0001212033,0.00002370606],"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":[0.0004878645,0.0003014186,0.01163505,0.00005540471,0.00009576428,0.0001111,0.00003177062,0.7422723,0.01092047,0.0008303296,0.001077267,0.2321812],"study_design_scores_gemma":[0.000002145475,0.000009983969,0.0005038492,3.86788e-7,0.000002644638,0.000003005741,7.95632e-7,0.9989796,0.0003602048,0.0001194392,0.00001680101,9.968066e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4723439,0.0003941161,0.524878,0.0001793762,0.000067453,0.00003247093,0.0003208974,0.0008025594,0.0009812792],"genre_scores_gemma":[0.9749682,0.00005482914,0.02424702,0.00001680068,0.00002416107,0.00001154707,0.000183481,0.00001375268,0.0004801165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003750008,"threshold_uncertainty_score":0.007456362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06258304265194171,"score_gpt":0.3005607635962115,"score_spread":0.2379777209442698,"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."}}