{"id":"W4387903192","doi":"10.1190/geo2023-0096.1","title":"Deep learning for high-resolution multichannel seismic impedance inversion","year":2023,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"National Natural Science Foundation of China","keywords":"Inversion (geology); Computer science; Regularization (linguistics); Inverse problem; Electrical impedance; Algorithm; Residual; Seismic inversion; High resolution; Geology; Geophysics; Artificial intelligence; Remote sensing; Seismology; Mathematics; Geometry","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001863701,0.0001063072,0.0001127222,0.00008469113,0.0003116957,0.00003072471,0.0001401122,0.00005494832,0.00004654402],"category_scores_gemma":[0.00005584368,0.0001013213,0.0000603269,0.0003141838,0.0000467107,0.0002002613,0.00001719197,0.000127697,0.0008863293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007177013,"about_ca_system_score_gemma":0.00001675304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002536084,"about_ca_topic_score_gemma":0.00001176386,"domain_scores_codex":[0.9991533,0.00003501633,0.0001134298,0.0002250786,0.000154315,0.0003188543],"domain_scores_gemma":[0.9995739,0.0001349504,0.00006323244,0.0001215466,0.00004860599,0.000057704],"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":[0.00007079127,0.00001779226,0.008291667,0.00009448483,0.00002428709,0.000007203649,0.0008876753,0.1461444,0.0007011016,0.0002562145,0.04424218,0.7992622],"study_design_scores_gemma":[0.0002246645,0.00009824819,0.008536299,0.0000161081,0.000009619731,7.5305e-7,0.0002564672,0.9697155,0.001269443,0.007248518,0.01249454,0.0001297883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9527118,0.00011825,0.04364732,0.0007916764,0.0008766443,0.0002947779,0.00002845762,0.0009478856,0.0005831612],"genre_scores_gemma":[0.995827,0.0001018301,0.001649482,0.0007572665,0.000199067,0.000003950777,0.0004261912,0.000006481623,0.00102875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8235711,"threshold_uncertainty_score":0.9998916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01422574840243291,"score_gpt":0.2173777690630708,"score_spread":0.2031520206606379,"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."}}