{"id":"W3175421494","doi":"10.1190/int-2021-0091.1","title":"Seismic characterization of a Triassic-Jurassic deep geothermal sandstone reservoir, onshore Denmark, using unsupervised machine learning techniques","year":2021,"lang":"en","type":"article","venue":"Interpretation","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"ARC Resources (Canada)","funders":"","keywords":"Geology; Facies; Geothermal gradient; Reservoir modeling; Geothermal exploration; Bayesian probability; Inversion (geology); Prestack; Petrophysics; Petrology; Paleontology; Geothermal energy; Petroleum engineering; Artificial intelligence; Seismology; Porosity; Geotechnical engineering; Computer science; Tectonics","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":[0.0003207091,0.0001438427,0.0002214754,0.0001879853,0.000120415,0.00005885405,0.0001415496,0.00009453027,0.00123018],"category_scores_gemma":[0.0001338508,0.0001366004,0.00008657205,0.0003197367,0.0000690169,0.0004252233,0.00001906157,0.000208901,0.00002112717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001888527,"about_ca_system_score_gemma":0.00007608761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001170923,"about_ca_topic_score_gemma":0.00005329381,"domain_scores_codex":[0.9986954,0.0002813876,0.0003580518,0.0002519821,0.0002285341,0.0001846358],"domain_scores_gemma":[0.9993095,0.00009572744,0.0002112754,0.0001692133,0.000162463,0.00005184967],"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":[0.0004600476,0.00006953845,0.139293,0.0001447659,0.00007614658,0.0000288631,0.002890712,0.002912775,0.2480095,0.00001589159,0.0001048865,0.6059938],"study_design_scores_gemma":[0.0001915913,0.00008601216,0.01388343,0.0001615011,0.00002850081,0.00002789166,0.0001852868,0.8166854,0.167542,0.0001183904,0.0009479345,0.0001419792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.942125,0.0002386024,0.05578049,0.0002741739,0.0001501163,0.0001415128,0.0000331456,0.0001438349,0.001113124],"genre_scores_gemma":[0.9937924,0.00009885151,0.00476604,0.0004565501,0.00004998987,0.000002199028,0.0005550059,0.00001033409,0.0002686516],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8137727,"threshold_uncertainty_score":0.9996828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01544110290187961,"score_gpt":0.2385746365900291,"score_spread":0.2231335336881495,"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."}}