Deep learning-based forward modeling and inversion techniques for computational physics problems / by Yinpeng Wang and Qiang Ren.
Material type:
TextPublication details: Boca Raton : CRC Press, Taylor & Francis Group, 2024Edition: 1stDescription: xiii, 185 p. ; 23 cmContent type: text Media type: computer Carrier type: online resourceSubject(s): Computational physics | Physics -- Data processing | Deep learning (Machine learning) | PhysicsAdditional physical formats: Print version:: Deep learning-based forward modeling and inversion techniques for computational physics problemsDDC classification: 530.0285631 Summary: "This book investigates in detail the emerging deep learning (DL) technique in computational physics, assessing its promising potential to substitute conventional numerical solvers for calculating the fields in real-time. After good training, the proposed architecture can resolve both the forward computing and the inverse retrieve problems. Pursuing a holistic perspective, the book includes the following areas. The first chapter discusses the basic DL frameworks. Then, the steady heat conduction problem is solved by the classical U-net in Chapter 2, involving both the passive and active cases. Afterwards, the sophisticated heat flux on a curved surface is reconstructed by the presented Conv-LSTM, exhibiting high accuracy and efficiency. Besides, the electromagnetic parameters of complex medium such as the permittivity and conductivity are retrieved by a cascaded framework in Chapter 4. Additionally, a physics-informed DL structure along with a nonlinear mapping module are employed to obtain the space/temperature/time-related thermal conductivity via the transient temperature in Chapter 5. Finally, in Chapter 6, a series of the latest advanced frameworks and the corresponding physics applications are introduced. As deep learning techniques are experiencing vigorous development in computational physics, more people desire related reading materials. This book is intended for graduate students, professional practitioners, and researchers who are interested in DL for computational physics"-- Provided by publisher.
| Item type | Current library | Home library | Call number | Status | Notes | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|---|---|
| Books | Jayakar Knowledge Resource Centre | Jayakar Knowledge Resource Centre | 530.0285631 WAN.Y (Browse shelf(Opens below)) | Available | 47.99 Pound | 524066 |
Includes bibliographical references and index.
"This book investigates in detail the emerging deep learning (DL) technique in computational physics, assessing its promising potential to substitute conventional numerical solvers for calculating the fields in real-time. After good training, the proposed architecture can resolve both the forward computing and the inverse retrieve problems. Pursuing a holistic perspective, the book includes the following areas. The first chapter discusses the basic DL frameworks. Then, the steady heat conduction problem is solved by the classical U-net in Chapter 2, involving both the passive and active cases. Afterwards, the sophisticated heat flux on a curved surface is reconstructed by the presented Conv-LSTM, exhibiting high accuracy and efficiency. Besides, the electromagnetic parameters of complex medium such as the permittivity and conductivity are retrieved by a cascaded framework in Chapter 4. Additionally, a physics-informed DL structure along with a nonlinear mapping module are employed to obtain the space/temperature/time-related thermal conductivity via the transient temperature in Chapter 5. Finally, in Chapter 6, a series of the latest advanced frameworks and the corresponding physics applications are introduced. As deep learning techniques are experiencing vigorous development in computational physics, more people desire related reading materials. This book is intended for graduate students, professional practitioners, and researchers who are interested in DL for computational physics"-- Provided by publisher.
Description based on print version record and CIP data provided by publisher.
There are no comments on this title.