Bernhard Eidel (Editor) | GPT for Python-Coding in Computational Materials Science and Mechanics. From Prompt Engineering to Solutions in Worked-Out Examples (Studies in Computational Intelligence 1198) (2025) [PDF]
Автор: Bernhard Eidel (Editor)
Издательство: Springer
ISBN: 978-3031854699, 978-3031854705
Жанр: Компьютерная литература
Язык: Английский
Формат: PDF
Качество: Изначально электронное (ebook)
Иллюстрации: Цветные и черно-белые
Описание:This book covers all the topics about ChatGPT required to successfully generate Python code to solve problems in computational materials science and mechanics, complemented by numerous fully worked-out applications. The complete work flow for AI-assisted coding is given, including: (i) prompt engineering providing a powerful toolset for how to give coding assignments to ChatGPT effectively; (ii) commented code listings; and (iii) tips and tricks to verify the codes in rigorous tests including human interventions to fix issues and gaps. Finally, (iv) the coding projects are critically reviewed to address the strengths and remaining weaknesses of the Chatbot, including explicit recommendations on how to communicate with GPT. For the steps (i)–(iv) the book presents a curated selection of intriguing problems from computational materials science and computational mechanics including machine learning for problem-solving. These problems are carefully chosen for their relevance to current research and industrial applications and their suitability for showcasing the advanced capabilities of GPT-4 for code generation. Spanning from predicting material behavior under various conditions to simulating complex mechanical interactions, the problems serve as a canvas on which GPT-4 paints its solutions, demonstrating not just accuracy but creativity in problem-solving. Therefore, the book serves as a valuable primer for both undergraduate and graduate students, as well as a review for research scientists and practicing engineers.
Front Matter
Topics of Computational Materials Science
Generation of Atomic Scale Single Crystals
Molecular Dynamics Simulation of Noble Gases
Phase Field Modeling of Grain Growth
Modeling Corrosion Using a Cellular Automaton
Instationary Heat Conduction on Rectangular Domains with Arbitrary Circular Holes
Topics of Deep Learning Based Materials Science
Transfer Learning for Alloy Classification Based on Microstructure Images
Transfer Learning for Microstructure Image Segmentation
Topics of Computational Analysis of Waves and Fluid Mechanics
Elastic Wave Propagation
Electromagnetic Wave Propagation in Dielectric Media
Flow Around an Obstacle Using the Lattice Boltzmann Method
Conclusions
Learned Lessons—Recommendations
Back Matter
Скриншоты:
Время раздачи: с 10 до 20 (минимум до появления первых 3-5 скачавших) 
