{"id":"W3016406005","doi":"10.1007/s10596-019-09859-y","title":"A deep learning approach to the inversion of borehole resistivity measurements","year":2020,"lang":"en","type":"article","venue":"Computational Geosciences","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Ministerio de Economía y Competitividad; Eusko Jaurlaritza; European Commission","keywords":"Borehole; Inversion (geology); Hydrogeology; Electrical resistivity and conductivity; Geology; Well logging; Piecewise; Electrical resistivity tomography; Inverse problem; Logging while drilling; Inverse transform sampling; Artificial neural network; Drilling; Geophysics; Geotechnical engineering; Computer science; Artificial intelligence; Engineering; Mathematics; Seismology; Mechanical engineering; Mathematical analysis","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":[0.0004168055,0.0000620161,0.00009830827,0.00002842725,0.0002426861,0.00003119934,0.0002915092,0.00001555695,0.00005661187],"category_scores_gemma":[0.0004420131,0.00003745174,0.00003838895,0.0008773882,0.0001006233,0.00008165155,0.00002392979,0.00009285018,0.00008295855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001702965,"about_ca_system_score_gemma":0.00003338862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000325004,"about_ca_topic_score_gemma":0.00002138247,"domain_scores_codex":[0.9987941,0.0001752556,0.0001206816,0.0002157293,0.0005460565,0.0001481891],"domain_scores_gemma":[0.9994532,0.000251366,0.00005594344,0.00004138199,0.00006912761,0.0001289672],"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":[0.00002039751,0.00001910044,0.02969239,0.000008205056,0.000003629377,1.871293e-7,0.000411278,0.7841036,0.0000261585,0.0001254956,0.0001669673,0.1854226],"study_design_scores_gemma":[0.0000392964,0.0001243441,0.4848475,0.000001751669,0.000002697924,2.194418e-7,0.00005331718,0.5123689,0.0000346383,0.001660026,0.0008268144,0.00004043659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.687764,0.0002910682,0.291347,0.006992516,0.0001850324,0.000317265,0.00001158017,0.00004879178,0.01304271],"genre_scores_gemma":[0.9754671,9.263704e-7,0.02365885,0.0007713373,0.00005736407,7.176166e-7,0.00001183191,6.659016e-7,0.00003113755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4551551,"threshold_uncertainty_score":0.186657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0646514646031894,"score_gpt":0.2550086888503261,"score_spread":0.1903572242471367,"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."}}