{"id":"W4389510675","doi":"10.2139/ssrn.4659072","title":"Enhanced Industrial Process Modeling with Transfer-Incremental-Learning: A Parallel Sae Approach and its Application to a Sulfur Recovery Unit","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Process (computing); Unit (ring theory); Sulfur; Process engineering; Transfer of learning; Computer science; Transfer (computing); Process modeling; Chemistry; Parallel computing; Chemical engineering; Engineering; Artificial intelligence; Process optimization; Mathematics; Organic chemistry; Mathematics education","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001233718,0.0004481126,0.000564172,0.0003141784,0.0001701306,0.0001234227,0.0003207438,0.0003963707,0.000001257595],"category_scores_gemma":[0.00004959726,0.000447806,0.00008752046,0.0003707466,0.00001078336,0.0002554416,0.00005522314,0.004459308,0.000007278083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009861712,"about_ca_system_score_gemma":0.0009377802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003040053,"about_ca_topic_score_gemma":0.0003129914,"domain_scores_codex":[0.9968073,0.0001233311,0.0006652286,0.0005538226,0.0003894626,0.001460803],"domain_scores_gemma":[0.9992535,0.00003004069,0.0001492502,0.0002101155,0.0001891859,0.0001679607],"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":[0.0002443583,0.0000179465,0.00003579756,0.0001221059,0.0003922666,8.328179e-7,0.0002971504,0.991087,0.001169938,0.0007303925,9.288607e-7,0.005901233],"study_design_scores_gemma":[0.002090067,0.0003148617,0.00000970942,0.0003041499,0.0001483075,0.0000798159,0.001441916,0.9891938,0.0001615888,0.00565668,0.00001576625,0.0005833624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2260121,0.0007836681,0.7712229,0.00004562632,0.0001319431,0.00133844,0.000005969896,0.0003130703,0.000146291],"genre_scores_gemma":[0.9947205,0.002923124,0.000782982,0.000007607774,0.0005418073,0.0005534645,0.00008825248,0.0001862034,0.000196102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7704399,"threshold_uncertainty_score":0.9997973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02082776453620693,"score_gpt":0.2359730725958935,"score_spread":0.2151453080596865,"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."}}