{"id":"W4310136636","doi":"10.1016/j.petrol.2022.111300","title":"Screening of waterflooding using smart proxy model coupled with deep convolutional neural network","year":2022,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Proxy (statistics); Convolutional neural network; Computer science; Petroleum engineering; Geology; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007866307,0.0001630987,0.0001910745,0.0002243934,0.0003038758,0.00003868627,0.0001899852,0.00002605501,0.000006552173],"category_scores_gemma":[0.00002801445,0.0001608767,0.00002718029,0.0008104674,0.00007340738,0.0003792219,0.0001207597,0.0001875453,7.121681e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000872234,"about_ca_system_score_gemma":0.00003813345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001665406,"about_ca_topic_score_gemma":4.814624e-7,"domain_scores_codex":[0.998565,0.00001148234,0.0002142002,0.0001913474,0.000493234,0.0005247274],"domain_scores_gemma":[0.9995794,0.00004380863,0.00002940645,0.0001527017,0.00006321099,0.0001314739],"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":[0.00000687599,0.000003655852,0.0007129506,0.00003170491,0.00001453086,0.000001502692,0.0001117759,0.987192,0.01102122,0.0007575448,0.000002102787,0.0001440675],"study_design_scores_gemma":[0.0002432402,0.0000256274,0.0006529708,0.0000212946,0.000009905245,0.00003272104,0.00005145092,0.997954,0.000720252,0.00001640442,0.00006934064,0.0002028349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5968408,0.0002411052,0.4025677,0.000003221798,0.0001509044,0.00004635651,0.000001581925,0.0001073496,0.00004092108],"genre_scores_gemma":[0.8927619,0.000006830679,0.1071051,0.000008301652,0.00005843606,0.00001813929,0.000003346609,0.00002726868,0.00001073533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2959211,"threshold_uncertainty_score":0.6560361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01804920852621841,"score_gpt":0.2208586335992399,"score_spread":0.2028094250730215,"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."}}