{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004063788,0.0006336826,0.001244933,0.0003251325,0.0004482372,0.0008081183,0.001382749,0.0008637325,0.005782793],"category_scores_gemma":[0.0009333952,0.0003301458,0.0004410984,0.0003318397,0.0003519583,0.0008625347,0.001174229,0.001393177,0.0008610758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006894578,"about_ca_system_score_gemma":0.001537189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006282601,"about_ca_topic_score_gemma":0.008060081,"domain_scores_codex":[0.9997182,0.00003232164,0.0000105832,0.00008878492,0.00007266704,0.00007735175],"domain_scores_gemma":[0.9996573,0.0001133529,0.00003231057,0.0000365983,0.00008729423,0.00007317436],"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":[0.0003970491,0.00024595,0.00125685,0.00009082915,0.00005698076,0.0001917153,0.00005368573,0.7467985,0.008303526,0.006753878,0.006126471,0.2297245],"study_design_scores_gemma":[0.00001098337,0.0000291245,0.00005070116,0.000002828747,0.000006755927,0.00001368088,0.000004317736,0.9981135,0.0005782884,0.0009004699,0.0002857738,0.000003556302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04006225,0.0005400758,0.9493332,0.0002981336,0.0003213902,0.00007241249,0.0001069568,0.001970286,0.007295238],"genre_scores_gemma":[0.8816399,0.0001845084,0.1080891,0.0002777503,0.00008097613,0.00006841092,0.0001748047,0.0001179071,0.009366735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006282601,"threshold_uncertainty_score":0.01934534,"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."}}