{"id":"W4390574546","doi":"10.1016/j.ijhydene.2023.12.298","title":"Machine learning - based shale wettability prediction: Implications for H2, CH4 and CO2 geo-storage","year":2024,"lang":"en","type":"article","venue":"International Journal of Hydrogen Energy","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"University of Science and Technology Beijing; Australian Research Council; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Wetting; Oil shale; Shale gas; Computer science; Environmental science; Geology; Petroleum engineering; Materials science; Composite material","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006841913,0.0003643977,0.0004741871,0.0005498452,0.0002390604,0.0006995748,0.0004191373,0.000492628,0.001040201],"category_scores_gemma":[0.002150267,0.00016769,0.0003067892,0.0004173991,0.000215807,0.0008863773,0.0002733558,0.0004458969,0.0003496152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005508961,"about_ca_system_score_gemma":0.0005889544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007482439,"about_ca_topic_score_gemma":0.008538052,"domain_scores_codex":[0.9999006,0.00002840474,0.000007378962,0.00002755914,0.00002168409,0.00001439854],"domain_scores_gemma":[0.999199,0.0004212891,0.0000884781,0.00005549331,0.0001990945,0.0000366645],"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":[0.0004792267,0.0003365229,0.03967128,0.00008362857,0.0001091748,0.00005148989,0.00003287239,0.841348,0.0131465,0.000781611,0.001002889,0.1029567],"study_design_scores_gemma":[0.000003268358,0.00001257385,0.002127219,0.000002053291,0.000002763933,0.000002561482,0.000003403277,0.9965318,0.0009615052,0.0003062817,0.00004354533,0.000002969855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9150844,0.0006816981,0.07989521,0.0005972103,0.00005260151,0.00002984947,0.0005831239,0.0005968726,0.002479129],"genre_scores_gemma":[0.9917984,0.0001142645,0.00730313,0.00003745812,0.00001694335,0.000009104667,0.0002424125,0.00001336168,0.0004650125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007482439,"threshold_uncertainty_score":0.0148778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126037133067867,"score_gpt":0.2436022727475302,"score_spread":0.2323419014168515,"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."}}