Unlock the power of AI and ML in engineering and applied sciences with this comprehensive guide byProfessor Muhammad Sahimi. From fluid dynamics to biological phenomena, discover cutting-edgeapplications and insights that drive innovation in your field.
Preface1 Artificial Intelligence and Complex Systems: What It Can and Cannot Do1.0 Introduction1.1 A Glance at History1.2 Complex Media and Systems1.3 Three Types of Complex Systems1.4 Physics-Informed and Data-Driven Approach to Complex Media and Phenomena1.5 What Artificial Intelligence Cannot Do2 Neural Networks and Other Machine-Learning Algorithms2.0 Introduction2.1 Training of Neural Networks: Backpropagation2.2 Classification of Learning2.3 Weak Learners and Boosting Algorithms2.4 Activation Functions2.5 Types of Neural Networks2.6 Training of Large Neural Networks2.7 Other Machine-Learning Algorithms2.8 Methods of Minimizing the Loss Function2.9 Challenges and Future Directions3 Solving Differential and Partial Differential Equations3.0 Introduction3.1 Solving Ordinary Differential Equations3.2 Solving Partial Differential Equations3.3 Solving High-Dimensional Pa
rtial Differential Equations: Deep BSDE Algorithm3.4 Feynman-Kac Solution for Backward Kolmogorov Equation of Stochastic Processes3.5 Data-Driven Discretization of Partial Differential Equations3.6 Other Models3.7 Space-Time Fractional Partial Differential Equations3.8 Challenges and Future Directions4 Fluid Mechanics: Single-Phase Flow4.0 Introduction4.1 The Microscopic Conservation Laws4.2 A Glance at History4.3 Kinematics of Fluid Flow4.4 Dynamics of Fluid Flow4.5 Modeling Flow Systems of Type I4.6 Data-Driven Neural Networks for Flow Systems of Type I4.7 Physics-Informed and Data-Driven Machine-Learning Approach4.8 Turbulent Flows4.9 Control of a Flow Field4.10 Aerodynamic Systems4.11 Machine Learning for Accelerating Direct Numerical Simulations4.12 Challenges and Future Directions5 Fluid Mechanics: Multiphase Flows5.0 Introduction5.1 Physics-Informed Simulation of Two-Phase Flow
s5.2 Data-Driven Approach to Simulating Two-Phase Flows5.3 Multiphase Flow in Heterogeneous Porous Materials and Media5.4 Challenges and Future Directions6 Heat and Mass Transfer Processes6.0 Introduction6.1 Heat and Mass Transfer Processes6.2 Applications of Neural Networks to Heat Transfer Processes6.3 Mass Transfer6.4 Challenges and Future Directions7 Porous Materials and Media7.0 Introduction7.1 Characterization of Core-Scale Porous media7.2 Characterization of Large-Scale Porous Media7.3 Reconstruction of Porous Media7.4 Data-Driven Neural Networks for Simulating Single-Phase Flow and Transport Processes7.5 Physics-Informed Neural Networks for Simulating Single-Phase Flow and Transport7.6 Two-Phase Flow7.7 Thermo-Hydro-Mechanical Processes7.8 Data-Driven Neural Networks for Two-Phase Flow7.9 Challenges and Future Directions8 Porous Materials and Media8.0 Introduction8.1
Quantum Monte Carlo Method8.2 First-Principle Simulation: Density-Functional Theory Calculations8.3 Molecular Dynamics Simulation8.4 Active Learning8.5 Other Aspects of Development of Force Fields by Machine Learning Algorithms8.6 Challenges and Future Directions9 Membranes for Separation of Fluid Mixtures9.0 Introduction9.1 Data-Driven Neural Networks for Separation Processes9.2 Data-Driven Approach for Designing and Screening of Membranes? Materials9.3 Application of Generative Adversarial Networks to Membrane Separation9.4 Data-Driven Neural Network for Minimizing Membrane Fouling9.5 Physics-Informed Modeling of Flow in Membranes9.6 Challenges and Future Directions10 Catalysis and Reaction Engineering10.0 Introduction10.1 Data-Driven Machine-Learning Algorithms for Predicting Catalytic Activity and Yield10.2 Data-Driven Machine-Learning Algorithms for Design and Optimizat
