{"id":"W4417309184","doi":"10.1002/cjce.70201","title":"Chemical process time series prediction using multi‐source transfer learning based on <scp>ESN</scp>","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Qingdao; Natural Science Foundation of Shandong Province","keywords":"Transfer of learning; Process (computing); Time series; Time domain; Fault (geology); Domain (mathematical analysis); Chemical process; Series (stratigraphy)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003043807,0.0001626434,0.0002109773,0.0001712598,0.0001623685,0.0001735716,0.0006860711,0.0001014242,0.00000210984],"category_scores_gemma":[0.0002592217,0.0001251573,0.0001133097,0.0004845075,0.00004825123,0.0001960548,0.00002833148,0.0008031256,9.985314e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001622784,"about_ca_system_score_gemma":0.0003401169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005792331,"about_ca_topic_score_gemma":0.000004905269,"domain_scores_codex":[0.9988919,0.00003038794,0.0003061214,0.000162517,0.0002209664,0.0003881192],"domain_scores_gemma":[0.9991712,0.000218621,0.00005733067,0.0001585578,0.0001151412,0.0002791315],"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":[0.000003141644,0.000006835789,0.00009466486,0.00003179236,0.00002013319,0.00001943782,0.0001914791,0.9541743,0.04462845,0.00007111573,0.00004984214,0.0007088213],"study_design_scores_gemma":[0.0002455112,0.00002192091,0.00002395604,0.0003250654,0.0000136934,0.00006614618,0.00000690602,0.9137127,0.0847517,0.00002413542,0.0007537134,0.00005449271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.668391,0.0001369042,0.3303279,0.0005972729,0.0002997282,0.00008380367,0.000001044726,0.00005920463,0.0001030963],"genre_scores_gemma":[0.9963182,5.464955e-7,0.003232754,0.0001424617,0.0002173849,0.000001234393,7.581326e-7,0.0000157472,0.00007092841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3279272,"threshold_uncertainty_score":0.5103765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006681910911622798,"score_gpt":0.1902471453256222,"score_spread":0.1835652344139994,"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."}}