{"id":"W4414051326","doi":"10.1016/j.icheatmasstransfer.2025.109635","title":"Inverse Convolutional Neural Network model for predicting the 3D protective bank profile and wall erosion inside a cylindrical electric arc furnace","year":2025,"lang":"en","type":"article","venue":"International Communications in Heat and Mass Transfer","topic":"Metallurgical Processes and Thermodynamics","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inverse; Convolutional neural network; Erosion; Artificial neural network; Approximation error; Mean squared error; Inverse problem; Electromagnetic shielding","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000136446,0.0005448929,0.0004240501,0.0003698154,0.0002144873,0.000376933,0.0005464697,0.0008271892,0.001499259],"category_scores_gemma":[0.000398943,0.0003907552,0.0005031919,0.0003024695,0.0002191159,0.0003228345,0.000315998,0.000719961,0.0002533689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000550883,"about_ca_system_score_gemma":0.0005866194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02452578,"about_ca_topic_score_gemma":0.01973472,"domain_scores_codex":[0.9999478,0.000006014006,0.000002500977,0.00001465512,0.00001761626,0.00001133708],"domain_scores_gemma":[0.9998941,0.00004668592,0.00001198984,0.000008530906,0.00002877449,0.000009814762],"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":[0.0001014814,0.00004562478,0.001980586,0.00002124572,0.00002351801,0.00009190111,0.00001308409,0.9762452,0.003575959,0.0002565101,0.0003946932,0.01725024],"study_design_scores_gemma":[9.056111e-7,0.000002939981,0.0002477978,5.405362e-7,0.0000014691,0.000002259713,0.000001095712,0.9994603,0.0002329883,0.0000291067,0.00001952999,0.000001103598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7539134,0.000629218,0.2373699,0.0003296128,0.0001201324,0.00003746941,0.0005967281,0.001827838,0.005175836],"genre_scores_gemma":[0.989016,0.0001073511,0.008237182,0.00002339369,0.00001020108,0.00001381779,0.0002378645,0.00002890948,0.002325354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02452578,"threshold_uncertainty_score":0.04876608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02366662042552059,"score_gpt":0.2606755361460316,"score_spread":0.237008915720511,"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."}}