{"id":"W4400969664","doi":"10.1016/j.marpetgeo.2024.107010","title":"Development of ensemble learning techniques and sequential model-based optimization for enhancing the generalizability of shale wettability predictions","year":2024,"lang":"en","type":"article","venue":"Marine and Petroleum Geology","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"High-end Foreign Experts Recruitment Plan of China; Ministry of Science and Technology, Croatia; National Natural Science Foundation of China","keywords":"Geology; Oil shale; Generalizability theory; Wetting; Petroleum engineering; Shale gas; Geochemistry; Paleontology; Statistics; Engineering; Chemical engineering","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":[0.0003565838,0.00007559528,0.0001550008,0.00007497103,0.00007391544,0.000008545021,0.00003919138,0.00006523162,0.00002512192],"category_scores_gemma":[0.00002350761,0.00005720302,0.00004083361,0.00006353632,0.00006794355,0.00002948776,0.00004490504,0.00009595019,6.567991e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001835145,"about_ca_system_score_gemma":0.00003685606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009602567,"about_ca_topic_score_gemma":0.0002448076,"domain_scores_codex":[0.9994515,0.00003058696,0.0002384795,0.0001292084,0.00004827414,0.0001019362],"domain_scores_gemma":[0.9997369,0.00009034686,0.00002389811,0.00009352972,0.00003427961,0.00002105155],"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":[0.000009784298,0.000009116795,0.002815261,0.0004344918,0.00005517819,2.380802e-7,0.0002301043,0.988142,0.002404682,0.00002200456,0.000007193115,0.005869937],"study_design_scores_gemma":[0.00008579409,0.00003053845,0.0002173372,0.00001249526,0.00004279871,0.000002397758,0.00003095699,0.9754536,0.02257355,0.0001011911,0.001398981,0.00005039469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4298337,0.0001910025,0.5695239,0.00006916342,0.00002519293,0.00005266009,0.000002351115,0.00005867724,0.0002434179],"genre_scores_gemma":[0.9707978,0.00006841575,0.02892207,0.000004083775,0.00002731168,0.00004069732,0.00002714402,0.00000842194,0.0001040932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5409641,"threshold_uncertainty_score":0.2332671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008691132854150008,"score_gpt":0.2283771339939228,"score_spread":0.2196860011397728,"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."}}