{"id":"W4379114187","doi":"10.1093/gji/ggad217","title":"Physics-guided deep-learning inversion method for the interpretation of noisy logging-while-drilling resistivity measurements","year":2023,"lang":"en","type":"article","venue":"Geophysical Journal International","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Inversion (geology); Robustness (evolution); Electrical resistivity and conductivity; Computer science; Geology; Synthetic data; Geophysics; Inverse transform sampling; Artificial intelligence; Algorithm; Seismology; Engineering; Electrical 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":[0.001278948,0.0001555721,0.00024689,0.0001078513,0.0003700956,0.00009646047,0.0004464786,0.000056492,0.0001559678],"category_scores_gemma":[0.0008510885,0.0001047151,0.0003020962,0.0004524037,0.00006784245,0.0002584411,0.00004007979,0.0004261805,0.0001128599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001891154,"about_ca_system_score_gemma":0.00003675796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002165729,"about_ca_topic_score_gemma":0.00002125278,"domain_scores_codex":[0.9979768,0.0003314558,0.0003815767,0.0002450408,0.0007455397,0.0003196257],"domain_scores_gemma":[0.9968002,0.002291636,0.0003126932,0.0001049848,0.0003761221,0.0001143976],"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":[0.0002690236,0.00005159233,0.004932539,0.00002176983,0.0002022121,0.000003286954,0.0002339729,0.1460425,0.002258227,0.0003127436,0.0007386056,0.8449336],"study_design_scores_gemma":[0.0003717802,0.0001713483,0.1256205,0.00003704127,0.00005207504,0.000006090931,0.00006697131,0.8484302,0.001303994,0.02235446,0.001464924,0.0001206898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1267961,0.00008055117,0.866887,0.002636011,0.001951558,0.0002977435,0.00003641258,0.00007948001,0.001235163],"genre_scores_gemma":[0.9849924,0.0000338167,0.01325672,0.0001949862,0.001093936,0.00000429236,0.00006335443,0.000007316515,0.0003532071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8581963,"threshold_uncertainty_score":0.4270159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06460664072445928,"score_gpt":0.3227572079528095,"score_spread":0.2581505672283502,"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."}}