{"id":"W4414143469","doi":"10.1016/j.geoen.2025.214190","title":"Leveraging machine learning to predict water flowback in tight-gas wells: Insights from low-pressure reservoirs in the Ordos Basin","year":2025,"lang":"en","type":"article","venue":"Geoenergy Science and Engineering","topic":"Hydraulic Fracturing and Reservoir Analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Workflow; Volume (thermodynamics); Hydraulic fracturing; Feature (linguistics); Artificial neural network; Support vector machine; Reservoir modeling; Perforation","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":[0.0006201302,0.000222018,0.0002533004,0.0007856903,0.0001701476,0.0001844911,0.0005869126,0.00008167332,0.00001739597],"category_scores_gemma":[0.0001265585,0.0001491095,0.00003914493,0.001438709,0.00005133406,0.0003228117,0.0001755921,0.0004728592,0.000008861785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008237052,"about_ca_system_score_gemma":0.00002664517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001989653,"about_ca_topic_score_gemma":0.0004694718,"domain_scores_codex":[0.9983477,0.0000395726,0.0002816954,0.0003976071,0.0003766477,0.0005568019],"domain_scores_gemma":[0.9994277,0.00009394975,0.00001028046,0.0003325398,0.00003191415,0.0001036573],"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":[0.000003845581,0.000008548801,0.00153202,0.00004418775,0.00001937481,0.00002384908,0.002179047,0.988006,0.007603799,0.00001576725,0.00006359176,0.0005000007],"study_design_scores_gemma":[0.0002415375,0.00001003568,0.01216477,0.0002339949,0.00001169619,0.000001593268,0.0004331325,0.9512125,0.01046728,0.00004638685,0.02497858,0.0001984736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945999,0.001018486,0.001678526,0.0007695963,0.0002527501,0.00009510646,0.000001585944,0.0001229849,0.001461079],"genre_scores_gemma":[0.9992352,0.0001577154,0.0001973934,0.0001393593,0.00006234375,0.00001811665,0.000007065891,0.0000170551,0.0001657104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03679346,"threshold_uncertainty_score":0.6080509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003648295471442578,"score_gpt":0.180662758936788,"score_spread":0.1770144634653454,"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."}}