Buch, Englisch, 346 Seiten, Format (B × H): 155 mm x 235 mm
ISBN: 978-3-032-48165-8
Verlag: Springer
This book provides a comprehensive exploration of computational approaches for discovering interpretable mathematical laws from scientific data. covers the foundations of symbolic regression, mathematical expression representations, evolutionary and neural search algorithms, and the integration of physical principles such as dimensional consistency, conservation laws, and symmetry constraints. It examines scientific data preparation, noise handling, experimental design, and the discovery of static relationships, ordinary differential equations, and partial differential equations, including graph-based approaches to spatiotemporal systems. Emerging directions, including deep learning integration, generative models, and agentic AI for automated scientific discovery, are also explored.
Bridging mathematics, physics, and artificial intelligence, the book emphasizes the transition from accurate prediction to meaningful scientific understanding. Through theoretical discussions, computational frameworks, and practical case studies, it addresses the challenges of interpretability, uncertainty, robustness, and scientific validation.
Written for researchers, graduate students, and practitioners in computational science, engineering, and machine learning, the book provides both methodological foundations and practical insights into how computational intelligence can support the discovery of new scientific knowledge.
Zielgruppe
Graduate
Autoren/Hrsg.
Fachgebiete
- Naturwissenschaften Physik Physik Allgemein Theoretische Physik, Mathematische Physik, Computerphysik
- Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Kybernetik, Systemtheorie, Komplexe Systeme
- Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
- Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Numerische Mathematik
Weitere Infos & Material
.- From Predictive Models to Scientific Laws.
.- Mathematical Languages for Symbolic Models.
.- Encoding Physics and Domain Knowledge.
.- Search and Optimization in SR.
.- Scientific Data, Noise, and Experimental Design.
.- Discovering Static Laws and Interpretable Surrogates.
.- Discovering Ordinary Differential Equations and Dynamical Systems.
.- PDEs, Fields, and Graph-Based Spatiotemporal Discovery.
.- Trustworthy Equation Discovery.
.- Extensions of SR: Hybrid and Agentic AI Systems.




