{"id":"W4385638436","doi":"10.1016/j.enggeo.2023.107255","title":"An integrated machine learning framework with uncertainty quantification for three-dimensional lithological modeling from multi-source geophysical data and drilling data","year":2023,"lang":"en","type":"article","venue":"Engineering Geology","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"National Key Research and Development Program of China; China Geological Survey; Hebei GEO University","keywords":"Machine learning; Artificial intelligence; Uncertainty quantification; Hyperparameter; Context (archaeology); Drilling; Bayesian inference; Geophysics; Geology; Computer science; Bayesian probability; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004576686,0.0001407594,0.0001841655,0.00008424106,0.0001531622,0.00004037123,0.0004778529,0.0001154425,0.00004006822],"category_scores_gemma":[0.0003359042,0.0001081132,0.00001127472,0.0001719481,0.00006693474,0.0002145849,0.00009671381,0.000360377,0.00001461409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002706344,"about_ca_system_score_gemma":0.00001845966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006327086,"about_ca_topic_score_gemma":0.000209616,"domain_scores_codex":[0.9988663,0.00004647326,0.0001546716,0.0005765256,0.0001013981,0.000254647],"domain_scores_gemma":[0.9988143,0.0004930876,0.00003981602,0.0005449006,0.00003383527,0.00007402552],"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":[0.00005178669,0.000008879068,0.03024991,0.000006987394,0.00001770972,0.000004539637,0.0000651248,0.9509569,0.00009396021,0.00002083686,0.00007656251,0.01844674],"study_design_scores_gemma":[0.0001693941,0.00009662722,0.006654113,0.00003079643,0.00001554489,0.000007247953,0.00005509087,0.9897553,0.00001262046,0.0002080812,0.002843462,0.0001516896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4081333,0.0001283182,0.590853,0.0001938115,0.00008145444,0.00007583113,0.0001799266,0.0003537095,6.692043e-7],"genre_scores_gemma":[0.8417277,0.00001783104,0.1446693,0.00008905539,0.00008777522,0.000001854844,0.01338475,0.000008506995,0.00001325546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4461837,"threshold_uncertainty_score":0.9564704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05776409894422477,"score_gpt":0.2664834752151824,"score_spread":0.2087193762709576,"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."}}