{"id":"W4402307267","doi":"10.1016/j.ifacol.2024.08.332","title":"Greenhouse Gas Emissions Reduction of a Hybrid-Powered Ferry using Deep Reinforcement Learning for Power Load Distribution","year":2024,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Maritime Transport Emissions and Efficiency","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Greenhouse gas; Reduction (mathematics); Reinforcement; Power (physics); Reinforcement learning; Environmental science; Automotive engineering; Greenhouse; Distribution (mathematics); Computer science; Engineering; Artificial intelligence; Mathematics; Ecology; Structural engineering; Physics; Biology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003088068,0.0001942785,0.0001966282,0.00004214846,0.000277142,0.00002980348,0.0001402471,0.00006982611,0.003640836],"category_scores_gemma":[0.00007201966,0.0001693165,0.0001689759,0.0003047416,0.0001265635,0.0002014827,0.00005756241,0.0001967126,0.00003301383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003503849,"about_ca_system_score_gemma":0.00006413482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003045715,"about_ca_topic_score_gemma":0.00001440896,"domain_scores_codex":[0.9984258,0.0000230363,0.0003942346,0.0004105442,0.0003890353,0.0003573772],"domain_scores_gemma":[0.9994851,0.00003356131,0.0000882788,0.0002067174,0.00002715627,0.0001591771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003303812,0.000566904,0.001239127,0.0002851959,0.00008753422,0.00005961595,0.002320236,0.3509355,0.6021363,0.00021781,0.000317073,0.04150438],"study_design_scores_gemma":[0.0008226685,0.000548439,0.0008004404,0.0004193938,0.0001732987,0.0001234544,0.0008454664,0.9556232,0.01223382,0.0001473377,0.02769411,0.00056838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8762281,0.0003696208,0.1198192,0.0004920025,0.0003542112,0.0005113044,0.00006044928,0.0001708876,0.001994176],"genre_scores_gemma":[0.9804381,0.00006947561,0.01687247,0.00001580886,0.00006008278,0.00001506579,0.0002448914,0.00002762061,0.002256538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6046877,"threshold_uncertainty_score":0.99727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01324525827202187,"score_gpt":0.2567819479108053,"score_spread":0.2435366896387835,"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."}}