{"id":"W4394984890","doi":"10.1016/j.jappgeo.2024.105362","title":"Simultaneous prediction of petrophysical properties and formation layered thickness from acoustic logging data using a modular cascading residual neural network (MCARNN) with physical constraints","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China; University of Alberta","keywords":"Petrophysics; Residual; Artificial neural network; Well logging; Computer science; Range (aeronautics); Modular design; Geology; Algorithm; Porosity; Geophysics; Artificial intelligence; Materials science; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002037097,0.0001446313,0.0002841809,0.00006617781,0.0001206077,0.0001078965,0.0001885486,0.00004923786,0.000005653896],"category_scores_gemma":[0.00001808572,0.0001011611,0.0000363628,0.0001645063,0.0001879586,0.0006515892,0.00003517282,0.0003712715,0.00000156625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001159825,"about_ca_system_score_gemma":0.00008181902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517675,"about_ca_topic_score_gemma":0.000003046318,"domain_scores_codex":[0.9989238,0.00004254609,0.0002879642,0.0001919725,0.0003683645,0.0001853332],"domain_scores_gemma":[0.9992562,0.0002315894,0.0002136226,0.0001612631,0.00007348824,0.00006382622],"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":[0.0005662888,0.00004843971,0.0003913878,0.0002666224,0.0001910783,0.0001272824,0.002510231,0.8362255,0.05392038,0.00006599631,0.0002492383,0.1054376],"study_design_scores_gemma":[0.000221359,0.0001872602,0.0003566489,0.0003127286,0.0001640459,0.0001226345,0.0008625725,0.9937122,0.002375611,0.001538869,0.00003996753,0.0001061196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809998,0.0002252168,0.0182389,0.00004549103,0.0001622841,0.0001043981,0.0001135341,0.00004233641,0.00006806814],"genre_scores_gemma":[0.995693,0.00002602779,0.003406614,0.00005857168,0.0007542964,2.255167e-7,0.00005175995,0.000007930907,0.00000152019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1574867,"threshold_uncertainty_score":0.4125228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03208486175354609,"score_gpt":0.2200534399171683,"score_spread":0.1879685781636222,"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."}}