Sophisticated Electromagnetic Forward Scattering Solver via Deep Learning

This book explores the potential of deep learning (DL) techniques in electromagnetic (EM) near-field scattering problems, offering a faster and more accurate solution compared to traditional numerical solvers. It is suitable for graduate students, professional practitioners, and researchers interested in computational electromagnetics and EM scattering.

Format: Paperback / softback
Length: 125 pages
Publication date: 21 October 2022
Publisher: Springer Verlag, Singapore

This comprehensive book delves into the realm of deep learning (DL) techniques in electromagnetic (EM) near-field scattering problems, exploring their potential to revolutionize real-time forecast scenarios by replacing traditional numerical solvers. EM scattering research has garnered interest from diverse fields, including antenna design, geophysical exploration, and remote sensing. Taking a holistic approach, the book introduces the entire workflow of utilizing the DL framework to tackle scattering problems. By training the proposed model on medium-scale data sets, precise approximations can be achieved, resulting in a framework that outperforms conventional FDFD solvers by three orders of magnitude. Notably, the scheme accommodates both 2D and 3D scatterers, making it highly applicable to a wide range of scenarios. This book is specifically designed for graduate students interested in applying deep learning to computational electromagnetics, professional practitioners working on EM scattering, and other related researchers.

Weight: 232g
Dimension: 235 x 155 (mm)
ISBN-13: 9789811662638
Edition number: 1st ed. 2022