{"id":"W2004133582","doi":"10.2118/170113-ms","title":"An Integrated Application of Cluster Analysis and Artificial Neural Networks for SAGD Recovery Performance Prediction in Heterogeneous Reservoirs","year":2014,"lang":"en","type":"article","venue":"SPE Heavy Oil Conference-Canada","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Artificial neural network; Computer science; Cluster analysis; Data mining; Curse of dimensionality; Principal component analysis; Robustness (evolution); Sensitivity (control systems); Machine learning; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007199314,0.0006359381,0.0004568735,0.00101835,0.0003446113,0.0005757411,0.0004871034,0.0005489625,0.0003331431],"category_scores_gemma":[0.001244187,0.0002560142,0.0004599807,0.000669354,0.0002640407,0.0004584907,0.0003930428,0.0002518616,0.00006075502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008684534,"about_ca_system_score_gemma":0.0005558878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01672907,"about_ca_topic_score_gemma":0.01064755,"domain_scores_codex":[0.9997764,0.00007322196,0.00001725255,0.00005661761,0.00005398534,0.00002248736],"domain_scores_gemma":[0.9994383,0.0002665943,0.00006579928,0.00004241253,0.0001683018,0.00001849311],"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":[0.00004297545,0.00003842253,0.002476217,0.000009804628,0.00001747911,0.00002873212,0.00001573171,0.9865037,0.001048529,0.0001331088,0.00004891741,0.009636366],"study_design_scores_gemma":[6.109993e-7,0.000007673722,0.00034552,6.545183e-7,0.00000156903,9.520261e-7,0.00000407768,0.9992644,0.0003112852,0.00005090928,0.00001084275,0.000001548141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8332167,0.0001210611,0.1638668,0.0001239636,0.00001897016,0.00008818836,0.0001224381,0.000400709,0.002041077],"genre_scores_gemma":[0.9922028,0.00002328494,0.007487682,0.000003796163,0.000001939837,0.00001880148,0.00003827909,0.000005600977,0.0002179423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01672907,"threshold_uncertainty_score":0.03326339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01438469741963504,"score_gpt":0.2312781021404642,"score_spread":0.2168934047208292,"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."}}