{"id":"W4360603407","doi":"10.1016/j.geoen.2023.211719","title":"Optimization of machine learning approaches for shale gas production forecast","year":2023,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; University of Calgary","keywords":"Overfitting; Machine learning; Computer science; Artificial intelligence; Random forest; Production (economics); Process (computing); Workflow; Bayesian optimization; Kernel (algebra); Data mining; Mathematics; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007056395,0.0001046127,0.0001227374,0.0003576597,0.00009528186,0.00003232145,0.0000983858,0.00003825124,0.000001930908],"category_scores_gemma":[0.0003309683,0.0001063566,0.00002478899,0.000997097,0.00004026578,0.0002690441,0.00002697714,0.00007056321,5.312152e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002644799,"about_ca_system_score_gemma":0.00001160358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004601506,"about_ca_topic_score_gemma":6.62564e-7,"domain_scores_codex":[0.999227,0.000004671443,0.0001552624,0.0001762666,0.0001786548,0.0002581147],"domain_scores_gemma":[0.9996887,0.00005020133,0.00001837179,0.0001101965,0.00007087678,0.00006159778],"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":[0.000001873016,0.00000174947,0.00006646839,0.0001125044,0.00000586475,1.614911e-7,0.0001247095,0.9882877,0.005527189,0.0003175507,0.00001287549,0.005541308],"study_design_scores_gemma":[0.0001105226,0.00001928676,0.0002726016,0.00002120899,0.000004285491,0.000002830021,0.00003958716,0.9906504,0.007952581,0.00002351914,0.0007924224,0.0001108058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4406787,0.0001733106,0.5580502,0.00003202056,0.0003496672,0.0001072329,0.000002553228,0.0004768717,0.0001295563],"genre_scores_gemma":[0.9481956,0.0001516747,0.05137417,0.000001011048,0.00008101486,0.00003702565,0.00001808056,0.00002772347,0.0001136955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.507517,"threshold_uncertainty_score":0.4337095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03581522684133086,"score_gpt":0.2330183323921366,"score_spread":0.1972031055508057,"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."}}