{"id":"W3041078355","doi":"10.2118/199082-ms","title":"Machine Learning Applied to SRV Modeling, Fracture Characterization, Well Interference and Production Forecasting in Low Permeability Reservoirs","year":2020,"lang":"en","type":"article","venue":"SPE Latin American and Caribbean Petroleum Engineering Conference","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Hydraulic fracturing; Permeability (electromagnetism); Discretization; Artificial neural network; Autoencoder; Fracture (geology); Reservoir modeling; Reservoir simulation; Machine learning; Artificial intelligence; Geology; Computer science; Petroleum engineering; Geotechnical engineering; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001663019,0.0003180918,0.0004505466,0.0001790566,0.00007212178,0.0001093485,0.0001600522,0.0000762726,0.00003272719],"category_scores_gemma":[0.000196597,0.00032081,0.00003870947,0.0004399266,0.00005705503,0.0001187683,0.00009656255,0.0007066393,0.000004738031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005676459,"about_ca_system_score_gemma":0.00001829461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002342869,"about_ca_topic_score_gemma":0.00010733,"domain_scores_codex":[0.9985324,0.00003207403,0.0003559774,0.0005298316,0.0001755377,0.0003742361],"domain_scores_gemma":[0.9993818,0.00003839521,0.00005924835,0.0002016331,0.00004832047,0.0002705915],"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":[0.00002262218,0.000008550229,0.004351274,0.0002104712,0.00002518243,0.000004743329,0.002320329,0.9828139,0.006009922,0.000009078315,0.000004983041,0.004218959],"study_design_scores_gemma":[0.0001696383,0.00006676288,0.00775917,0.0001097108,0.00001666105,0.000002719157,0.0004964211,0.989933,0.0005258761,0.000006744876,0.0005718724,0.0003413966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8236524,0.0000596667,0.1742923,0.001117421,0.00005433613,0.0001444155,0.000009608798,0.0002817775,0.0003881232],"genre_scores_gemma":[0.9984382,0.0001516279,0.001006594,0.0001268476,0.0001200411,0.00002472442,0.00004826884,0.00004809279,0.00003554574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1747859,"threshold_uncertainty_score":0.9999244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01046455374876857,"score_gpt":0.1891883364493932,"score_spread":0.1787237827006246,"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."}}