Sahimi Artificial Intelligence in Science and Engineering

From Porous Materials to Drug Discovery
1. Auflage 2026
ISBN: 978-3-527-85192-8
Verlag: Wiley-VCH
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 813 Seiten, E-Book

Apply AI and ML to solve complex problems across sciences
 
Many problems in physics, engineering, and applied sciences resist traditional modeling approaches. Artificial Intelligence in Science and Engineering: From Porous Materials to Drug Discovery presents AI and ML methods for tackling otherwise unsolvable problems in complex systems. Written by Muhammad Sahimi, who brings over 40 years of research experience to the topic, this reference spans multiple scientific domains.
 
The book covers AI and ML applications in hydrodynamics, porous media characterization, molecular dynamics simulation, and biological phenomena including protein folding. It addresses environmental applications and drug discovery, connecting computational methods with domain-specific challenges in fluid dynamics, materials science, and biology. Readers gain access to methods that model, predict, and optimize processes difficult to approach through conventional techniques.
 
Readers will also find:
 
* Detailed treatment of AI and ML approaches applied to complex systems in fluid dynamics and porous media research
* Coverage of molecular dynamics applications where machine learning accelerates simulation and prediction of material properties
* Methods for protein folding prediction and drug discovery leveraging current artificial intelligence and computational biology techniques
* Environmental science applications demonstrating how AI-driven modeling addresses problems resistant to traditional analytical methods
* Cross-disciplinary frameworks connecting physics, engineering, materials science, and biology through unified computational approaches
 
Physicists, materials scientists, engineers, computer scientists, and computational biologists will find this volume a substantive reference for applying AI and ML across their research domains. By unifying coverage of diverse complex systems under one framework, the book serves both academics and practitioners working at the intersection of computation and applied science.

Autoren/Hrsg.

Sahimi, Muhammad

Inhaltsverzeichnis

Preface
 
1 Artificial Intelligence and Complex Systems: What It Can and Cannot Do
1.0 Introduction
1.1 A Glance at History
1.2 Complex Media and Systems
1.3 Three Types of Complex Systems
1.4 Physics-Informed and Data-Driven Approach to Complex Media and Phenomena
1.5 What Artificial Intelligence Cannot Do
 
2 Neural Networks and Other Machine-Learning Algorithms
2.0 Introduction
2.1 Training of Neural Networks: Backpropagation
2.2 Classification of Learning
2.3 Weak Learners and Boosting Algorithms
2.4 Activation Functions
2.5 Types of Neural Networks

2.6 Training of Large Neural Networks
2.7 Other Machine-Learning Algorithms
2.8 Methods of Minimizing the Loss Function
2.9 Challenges and Future Directions
 
3 Solving Differential and Partial Differential Equations
3.0 Introduction
3.1 Solving Ordinary Differential Equations
3.2 Solving Partial Differential Equations
3.3 Solving High-Dimensional Partial Differential Equations: Deep BSDE Algorithm
3.4 Feynman-Kac Solution for Backward Kolmogorov Equation of Stochastic Processes
3.5 Data-Driven Discretization of Partial Differential Equations
3.6 Other Models
3.7 Space-Time Fractional Partial Differential Equations
3.8 Challenges and Future Directions
 
4 Fluid Mechanics: Single-Phase Flow
4.0 Introduction
4.1 The Microscopic Conservation Laws
4.2 A Glance at History
4.3 Kinematics of Fluid Flow
4.4 Dynamics of Fluid Flow
4.5 Modeling Flow Systems of Type I
4.6 Data-Driven Neural Networks for Flow Systems of Type I
4.7 Physics-Informed and Data-Driven Machine-Learning Approach
4.8 Turbulent Flows
4.9 Control of a Flow Field
4.10 Aerodynamic Systems
4.11 Machine Learning for Accelerating Direct Numerical Simulations
4.12 Challenges and Future Directions
 
5 Fluid Mechanics: Multiphase Flows
5.0 Introduction
5.1 Physics-Informed Simulation of Two-Phase Flows
5.2 Data-Driven Approach to Simulating Two-Phase Flows
5.3 Multiphase Flow in Heterogeneous Porous Materials and Media
5.4 Challenges and Future Directions
 
6 Heat and Mass Transfer Processes
6.0 Introduction
6.1 Heat and Mass Transfer Processes
6.2 Applications of Neural Networks to Heat Transfer Processes
6.3 Mass Transfer
6.4 Challenges and Future Directions
 
7 Porous Materials and Media
7.0 Introduction
7.1 Characterization of Core-Scale Porous media
7.2 Characterization of Large-Scale Porous Media
7.3 Reconstruction of Porous Media
7.4 Data-Driven Neural Networks for Simulating Single-Phase Flow and Transport Processes
7.5 Physics-Informed Neural Networks for Simulating Single-Phase Flow and Transport
7.6 Two-Phase Flow
7.7 Thermo-Hydro-Mechanical Processes
7.8 Data-Driven Neural Networks for Two-Phase Flow
7.9 Challenges and Future Directions
 
8 Porous Materials and Media
8.0 Introduction
8.1 Quantum Monte Carlo Method
8.2 First-Principle Simulation: Density-Functional Theory Calculations
8.3 Molecular Dynamics Simulation
8.4 Active Learning
8.5 Other Aspects of Development of Force Fields by Machine Learning Algorithms
8.6 Challenges and Future Directions
 
9 Membranes for Separation of Fluid Mixtures
9.0 Introduction
9.1 Data-Driven Neural Networks for Separation Processes
9.2 Data-Driven Approach for Designing and Screening of Membranes? Materials
9.3 Application of Generative Adversarial Networks to Membrane Separation
9.4 Data-Driven Neural Network for Minimizing Membrane Fouling
9.5 Physics-Informed Modeling of Flow in Membranes
9.6 Challenges and Future Directions
 
10 Catalysis and Reaction Engineering
10.0 Introduction
10.1 Data-Driven Machine-Learning Algorithms for Predicting Catalytic Activity and Yield
10.2 Data-Driven Machine-Learning Algorithms for Design and Optimization of New Catalysts
10.3 Data-Driven Neural Networks for Predicting Potential Energy Surface in Catalysis
10.4 Applications of Behler-Parrinello Generalized Neural-Network Representation of High-Dimensional Potential Energy Surfaces
10.5 Machine-Learning Approach for Discovering and Designing New Catalysts Using Density-Functional Theory Data
10

Über Autor(innen)

Muhammad Sahimi, PhD, is a professor of chemical engineering and materials science at the
University of Southern California, USA. With over 40 years of experience, he specializes in porous
media, heterogeneous materials, and the application of AI and ML methods. He has published more
than 400 peer-reviewed articles and four books.