{"id":"W7133079662","doi":"","title":"Comparing Deep Learning Against Classic Time Series Analysis and System Identification for Modelling the Kraft Chemical Recovery Process","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Kraft paper; Process (computing); Kraft process; Time series; Deep learning; Process modeling; System identification; Process systems","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001870093,0.000980692,0.0004931155,0.0005089265,0.0002106614,0.0007830212,0.0004504478,0.0008218024,0.001920719],"category_scores_gemma":[0.004054224,0.000231395,0.0005265538,0.0003902968,0.0003514108,0.001330945,0.0006522891,0.001917513,0.0003635766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038442,"about_ca_system_score_gemma":0.0009011578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009271656,"about_ca_topic_score_gemma":0.006260064,"domain_scores_codex":[0.9996069,0.0001465707,0.00003018431,0.00007464721,0.00009993694,0.00004172309],"domain_scores_gemma":[0.9976764,0.001736178,0.0001454319,0.0001192741,0.0002638555,0.00005879249],"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":[0.0002295181,0.00009665761,0.001398126,0.0001271978,0.00007196135,0.00001693479,0.00002674615,0.9522246,0.00106912,0.003294421,0.0006284888,0.04081632],"study_design_scores_gemma":[0.000004687504,0.00004501929,0.0003640337,0.00001075001,0.000008368709,0.000001967317,0.000007123447,0.9974909,0.0005695283,0.001266016,0.0002284281,0.000003161752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6899132,0.004427786,0.2832092,0.002929081,0.0002723496,0.0001101633,0.0008729603,0.001326846,0.01693839],"genre_scores_gemma":[0.9527335,0.001493768,0.04149615,0.0001712075,0.00004688455,0.00005591832,0.0006392544,0.00006546473,0.003297868],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009271656,"threshold_uncertainty_score":0.01843536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02006030115062989,"score_gpt":0.2716615994135727,"score_spread":0.2516012982629428,"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."}}