{"id":"W4322731021","doi":"10.1109/tmag.2023.3247023","title":"Physics-Informed Neural Networks for Inverse Electromagnetic Problems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Magnetics","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Electromagnetism; Inverse problem; Solver; Artificial neural network; Inverse; Set (abstract data type); Computer science; A priori and a posteriori; Electromagnetic coil; Field (mathematics); Electromagnetics; Electromagnetic field; Magnetostatics; Applied mathematics; Magnetic field; Physics; Artificial intelligence; Mathematical analysis; Mathematics; Geometry; Quantum mechanics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007171172,0.0008033304,0.0006473378,0.0004340534,0.0003136529,0.0007109772,0.001064809,0.001219282,0.002704765],"category_scores_gemma":[0.002511585,0.0005598721,0.0005652861,0.0006126483,0.0007758837,0.001124654,0.001165817,0.00206529,0.0006172219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007470392,"about_ca_system_score_gemma":0.0007831096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003167969,"about_ca_topic_score_gemma":0.003777677,"domain_scores_codex":[0.9997353,0.0001001089,0.00001384191,0.00005668659,0.00007366531,0.00002039573],"domain_scores_gemma":[0.9994831,0.0003543255,0.00004562975,0.00003824347,0.00006484275,0.00001389198],"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":[0.00001774671,0.00001389205,0.0001290223,0.00008293294,0.00002632123,0.00002543671,0.00002579178,0.9432005,0.001286394,0.02396108,0.0008118037,0.03041911],"study_design_scores_gemma":[0.000001591505,0.000003056504,0.00002675131,0.000004500764,0.000001894367,0.000003611764,0.000001562584,0.9884841,0.0001407276,0.0108369,0.0004931797,0.000002166487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003704397,0.0007467717,0.9923949,0.0002440319,0.00003360987,0.00002008124,0.00005300449,0.0001959096,0.002607265],"genre_scores_gemma":[0.4922372,0.003158812,0.4882451,0.0005445392,0.000297015,0.0005870496,0.0007018149,0.0002848191,0.01394364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003167969,"threshold_uncertainty_score":0.009048343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606488096901369,"score_gpt":0.257521841741794,"score_spread":0.2314569607727804,"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."}}