{"id":"W4386136950","doi":"10.1038/s41598-023-40904-0","title":"Hierarchical automated machine learning (AutoML) for advanced unconventional reservoir characterization","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Joint Research Centre; King Fahd University of Petroleum and Minerals","keywords":"Workflow; Machine learning; Oil shale; Computer science; Artificial intelligence; Gradient boosting; Volume (thermodynamics); Reservoir modeling; Porosity; Artificial neural network; Random forest; Geology; Petroleum engineering; Geotechnical engineering; Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001997727,0.0008794323,0.0007186778,0.001221043,0.0005962623,0.0008888642,0.001129754,0.0007944116,0.002173863],"category_scores_gemma":[0.003917863,0.0004231058,0.0008172274,0.0006108094,0.0005249085,0.0009421172,0.001144836,0.0009738847,0.000819752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101363,"about_ca_system_score_gemma":0.00182503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009342958,"about_ca_topic_score_gemma":0.01173221,"domain_scores_codex":[0.9991069,0.0003809582,0.00003984191,0.0001917165,0.0001919228,0.00008854296],"domain_scores_gemma":[0.9979815,0.001058967,0.000194073,0.0002668338,0.0004326358,0.00006589262],"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":[0.0001603636,0.0002664299,0.007796329,0.0001235856,0.00009457745,0.0001340228,0.0001163491,0.6740158,0.009703036,0.003427499,0.00321961,0.3009424],"study_design_scores_gemma":[0.000004122208,0.00001498537,0.0002547097,0.000002775666,0.000002920119,0.000005166838,0.000005725291,0.9974558,0.001138562,0.0008654197,0.0002463312,0.000003534068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07225811,0.0002228785,0.9137456,0.0003265469,0.00003074278,0.0001575055,0.0003592796,0.01094276,0.001956491],"genre_scores_gemma":[0.6100059,0.00006383686,0.3875632,0.0002132991,0.00002768408,0.000184904,0.0006301153,0.0001862231,0.001124751],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009342958,"threshold_uncertainty_score":0.01857716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01492890555035993,"score_gpt":0.2566566657987874,"score_spread":0.2417277602484274,"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."}}