Neural Network Predicts Ion Concentration Profiles under Nanoconfinement

Abstract

Modeling the ion concentration profile in nanochannel plays an important role in understanding the electrical double layer and electroosmotic flow. Due to the non-negligible surface interaction and the effect of discrete solvent molecules, molecular dynamics (MD) simulation is often used as an essential tool to study the behavior of ions under nanoconfinement. Despite the accuracy of MD simulation in modeling nanoconfinement systems, it is computationally expensive. In this work, we propose neural network to predict ion concentration profiles in nanochannels with different configurations, including channel widths, ion molarity, and ion types. By modeling the ion concentration profile as a probability distribution, our neural network can serve as a much faster surrogate model for MD simulation with high accuracy. We further demonstrate the superior prediction accuracy of neural network over XGBoost. Lastly, we demonstrated that neural network is flexible in predicting ion concentration profiles with different bin sizes. Overall, our deep learning model is a fast, flexible, and accurate surrogate model to predict ion concentration profiles in nanoconfinement.

References in corpus (25)

• Adam: A Method for Stochastic Optimization
• XGBoost: A Scalable Tree Boosting System
• Array Programming with NumPy
• The NumPy array: a structure for efficient numerical computation
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Machine Learning for Fluid Mechanics
• Exponential expressivity in deep neural networks through transient chaos
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Dipolar Poisson-Boltzmann Equation: Ions and Dipoles Close to Charged Surfaces
• Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations
• Differential capacitance of the electric double layer: The interplay between ion finite size and dielectric decrement
• Surface Tension of Electrolyte Interfaces: Ionic Specificity within a Field-Theory Approach
• Roundtrip: A Deep Generative Neural Density Estimator
• Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination
• Counterions at charge-modulated substrates
• Dipolar Poisson-Boltzmann Approach to Ionic Solutions: A Mean Field and Loop Expansion Analysis
• Graph Neural Networks Accelerated Molecular Dynamics
• Ionic Behavior in Highly Concentrated Aqueous Solutions Nanoconfined between Discretely Charged Silicon Surfaces
• Test-charge theory for the electric double layer
• Modeling nanoconfinement effects using active learning
• Revisiting the Poisson-Boltzmann theory: charge surfaces, multivalent ions and inter-plate forces
• A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions
• Ionic profiles close to dielectric discontinuities: Specific ion-surface interactions
• Ion filling of a one-dimensional nanofluidic channel in the interaction confinement regime
• Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks