{"id":"W4417214721","doi":"10.1016/j.compchemeng.2025.109520","title":"A risk-aware LNG terminal scheduling digital twin based on deep reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Spacecraft and Cryogenic Technologies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Petro-Canada","funders":"National Key Research and Development Program of China; Tsinghua University","keywords":"Reinforcement learning; Scheduling (production processes); Intuition; Control (management); Emulation; Stability (learning theory); Deep learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000590313,0.0003034755,0.0002558847,0.000238358,0.000054306,0.0001118724,0.000314234,0.0001699759,0.000008639567],"category_scores_gemma":[0.0001178277,0.0003304422,0.0001345875,0.0003378798,0.00002790955,0.0001107387,0.0001226544,0.0006630219,0.00001527314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002084115,"about_ca_system_score_gemma":0.00001449741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001412363,"about_ca_topic_score_gemma":6.829179e-8,"domain_scores_codex":[0.9988573,0.000003693953,0.0002604498,0.0002747426,0.000168538,0.0004353031],"domain_scores_gemma":[0.9994372,0.0001549599,0.00002978955,0.0002765736,0.00002076118,0.00008076718],"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":[0.000008400283,0.00000977988,0.0002261182,0.00009407892,0.0000498777,0.00001509617,0.00003004097,0.979279,0.005892671,0.0001274032,0.0001335383,0.01413401],"study_design_scores_gemma":[0.0004296149,0.00002663193,0.00007229317,0.0002745206,0.00001980737,0.000003546834,0.00003658051,0.969974,0.02718358,0.0000156402,0.00165513,0.0003086522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1768563,0.0001971267,0.8194206,0.00004822627,0.000371808,0.000114282,0.000001159429,0.002299971,0.0006905598],"genre_scores_gemma":[0.9921259,0.000009051786,0.007641023,0.00003309443,0.0000784432,0.00002730176,0.00001833049,0.00004100995,0.00002586073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8152696,"threshold_uncertainty_score":0.9999148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003488013847648561,"score_gpt":0.1831578114781993,"score_spread":0.1796697976305507,"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."}}