{"id":"W4399185692","doi":"10.3997/2214-4609.202410222","title":"SiameseFWI: A Deep Learning Model for Full Waveform Inversion","year":2024,"lang":"en","type":"article","venue":"","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Inversion (geology); Convolutional neural network; Deep learning; Artificial intelligence; Algorithm; Benchmark (surveying); Data modeling; Synthetic data; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001095373,0.0007853849,0.0005513329,0.0004951592,0.0003506204,0.0009941431,0.002102526,0.001011731,0.004030247],"category_scores_gemma":[0.0021732,0.000481504,0.0007584817,0.0005745383,0.0006857374,0.00145059,0.00131249,0.001941338,0.0009298841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00100972,"about_ca_system_score_gemma":0.001678312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01494851,"about_ca_topic_score_gemma":0.01630645,"domain_scores_codex":[0.9997779,0.00004301762,0.00001362098,0.00006652603,0.00006957768,0.00002941671],"domain_scores_gemma":[0.9995809,0.0001218781,0.00003323854,0.00008512579,0.0001445991,0.00003429249],"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":[0.00006635005,0.00003806741,0.0007843502,0.00003998091,0.00006498995,0.00004833642,0.00002347734,0.9106818,0.002971861,0.01305232,0.003970157,0.06825843],"study_design_scores_gemma":[0.000002102035,0.000006194306,0.00003895574,0.000001552953,0.000001517643,0.000004693882,9.894939e-7,0.9968678,0.0004191358,0.002278497,0.0003758804,0.000002591583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01604285,0.0002127088,0.9777197,0.0003659735,0.00006187795,0.00004998219,0.0005361159,0.00209113,0.002919672],"genre_scores_gemma":[0.552866,0.0003549784,0.4286621,0.0004081724,0.00008167206,0.0003263439,0.003221834,0.0005495403,0.0135294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01494851,"threshold_uncertainty_score":0.02972299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01847896207017192,"score_gpt":0.2274715224447282,"score_spread":0.2089925603745563,"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."}}