{"id":"W4406849570","doi":"10.1016/j.energy.2025.134738","title":"Interpretable predictive modelling of outlet temperatures in Central Alberta's hydrothermal system using boosting-based ensemble learning incorporating Shapley Additive exPlanations approach","year":2025,"lang":"en","type":"article","venue":"Energy","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Key Technologies Research and Development Program; BHP; National Key Research and Development Program of China; China Scholarship Council; National University of Singapore","keywords":"Boosting (machine learning); Hydrothermal circulation; Ensemble learning; Ensemble forecasting; Computer science; Predictive modelling; Artificial intelligence; Machine learning; Environmental science; Engineering; Chemical engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002209411,0.0001862569,0.0002939884,0.0003389233,0.00007734609,0.00003535784,0.0001216709,0.0001106981,0.00000540877],"category_scores_gemma":[0.00009740145,0.0002022137,0.00006408271,0.000435654,0.00002030081,0.0001421482,0.0000247293,0.0002644052,1.575177e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002006043,"about_ca_system_score_gemma":0.00006036425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007991903,"about_ca_topic_score_gemma":0.00003375137,"domain_scores_codex":[0.9988471,0.0001375557,0.0003956158,0.0002067759,0.0001403718,0.000272583],"domain_scores_gemma":[0.999342,0.0003395566,0.00007003774,0.0001417651,0.00005883328,0.00004779695],"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":[0.00001964983,0.00001502989,0.0009471239,0.0001391939,0.00004619993,0.00000221015,0.000451048,0.9938423,0.001820526,0.002587459,0.000008449041,0.000120783],"study_design_scores_gemma":[0.0003764648,0.00001361871,0.00004907691,0.0004884638,0.00001458517,0.000001206327,0.0004181143,0.9913547,0.00704462,0.00002963684,0.00005756564,0.0001519569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1486393,0.0001797469,0.8422979,0.000002557666,0.0001409361,0.00008682284,0.00001122575,0.0001414832,0.008500087],"genre_scores_gemma":[0.9720368,0.000002969768,0.02763131,0.000006086429,0.00004651701,0.00002398835,0.00006063651,0.00003482937,0.0001568853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8233975,"threshold_uncertainty_score":0.8246037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01375478906787581,"score_gpt":0.2262696759537256,"score_spread":0.2125148868858498,"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."}}