{"id":"W4381853487","doi":"10.1016/j.energy.2023.128255","title":"Comparative data-driven enhanced geothermal systems forecasting models: A case study of Qiabuqia field in China","year":2023,"lang":"en","type":"article","venue":"Energy","topic":"Geothermal Energy Systems and Applications","field":"Energy","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial neural network; Support vector machine; Geothermal gradient; Machine learning; Adaptability; Artificial intelligence; Computer science; Stability (learning theory); Data mining; Boosting (machine learning); Predictive modelling; 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":[0.0002207594,0.0002054506,0.0004740221,0.0002019801,0.0001086402,0.00002887283,0.0004312826,0.00009148152,0.00003978431],"category_scores_gemma":[0.00001592911,0.000189893,0.00004178004,0.0006982324,0.000025103,0.0002023564,0.0002270461,0.0001158501,0.00001210661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002921041,"about_ca_system_score_gemma":0.00003386914,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3536424,"about_ca_topic_score_gemma":0.05259993,"domain_scores_codex":[0.9982329,0.0001774419,0.0005829791,0.0004585682,0.0002173612,0.0003307302],"domain_scores_gemma":[0.9986439,0.0001735671,0.0002190994,0.000840846,0.00005259867,0.00006995675],"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":[0.00001716087,0.000207351,0.00007984521,0.00002240436,0.0000737036,0.0002454982,0.0047462,0.9802998,0.0006400663,0.01201405,0.0001284571,0.001525511],"study_design_scores_gemma":[0.0007670615,0.0001379448,0.0001592608,0.00005808655,0.00001509878,0.00008605581,0.01226247,0.9840999,0.000420649,0.0001474686,0.001639106,0.0002068674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849253,0.00007534053,0.001818634,0.00002224974,0.0001586036,0.0002223049,0.00002957359,0.0001253344,0.01262266],"genre_scores_gemma":[0.9979864,0.000006524635,0.0000569646,0.00001786354,0.0001351384,0.0002931072,0.00006557283,0.00003468843,0.001403777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3010425,"threshold_uncertainty_score":0.9646876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09455817088423595,"score_gpt":0.3024671937566222,"score_spread":0.2079090228723862,"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."}}