{"id":"W4361006473","doi":"10.3390/min13040461","title":"Retrieval of Subsurface Resistivity from Magnetotelluric Data Using a Deep-Learning-Based Inversion Technique","year":2023,"lang":"en","type":"article","venue":"Minerals","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada","funders":"","keywords":"Magnetotellurics; Inversion (geology); Electrical resistivity and conductivity; Computation; Convolutional neural network; Deep learning; Electrical resistivity tomography; Synthetic data; Artificial neural network; Geology; Computer science; Inverse transform sampling; Data processing; Artificial intelligence; Geophysics; Algorithm; Structural basin; Engineering; Geomorphology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007088654,0.0001186619,0.000242435,0.0001015709,0.00009138873,0.00001886196,0.0003600991,0.00009413077,0.0007114874],"category_scores_gemma":[0.0006858297,0.00009719386,0.00004981029,0.001307608,0.00006423285,0.0001122628,0.00005544522,0.0001954233,0.0001354843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003377383,"about_ca_system_score_gemma":0.0000380508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006562318,"about_ca_topic_score_gemma":0.0002314209,"domain_scores_codex":[0.9984989,0.0003876616,0.0002013808,0.0003555935,0.0002894493,0.0002670577],"domain_scores_gemma":[0.9985522,0.00084176,0.00009889525,0.0003692003,0.00003862215,0.0000993104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008350431,0.0001360892,0.08978487,0.0001719581,0.00005297067,0.0001233942,0.00009826196,0.09131853,0.6272845,0.000008301348,0.002515226,0.1876708],"study_design_scores_gemma":[0.0002275916,0.0002230255,0.1747013,0.00003010727,0.00003306441,7.171126e-7,0.00001098344,0.7825552,0.03805432,0.001245447,0.002720687,0.0001976507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938328,0.000209369,0.005062659,0.0001612555,0.00007737161,0.0001520621,0.0001695343,0.00008929973,0.000245655],"genre_scores_gemma":[0.9818726,0.00001495668,0.01681216,0.00005030413,0.00007005,2.681307e-7,0.0006076053,0.00000411668,0.0005679522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6912366,"threshold_uncertainty_score":0.9920305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05704854054214522,"score_gpt":0.2817316578056575,"score_spread":0.2246831172635123,"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."}}