Development of novel symbolic regression models for prediction of nano filters efficiency using CFD and DPM

This study presents a comprehensive CFD-DPM framework for analyzing the filtration performance of nanofiber media, with a specific focus on parameters relevant to face mask applications while maintaining general applicability. A detailed parametric study is conducted to assess the influence of inlet velocity, particles density and particle number density on filtration efficiency and pressure drop. The results demonstrate a complex, non-linear relationship between these parameters, where filtration efficiency is most sensitive to inlet velocity, exhibiting a decrease from approximately 96% to 42% as velocity increases. To understand these complex interactions, advanced Artificial Intelligence techniques are employed. An Artificial Neural Network model achieved exceptional predictive accuracy (R2 > 0.999) and is subsequently used for a global sensitivity analysis via the Morris method, which quantitatively ranked inlet velocity as the most influential parameter. Furthermore, a novel, highly accurate explicit correlation for predicting filtration efficiency is derived using Symbolic Regression, achieving a coefficient of determination R2 > 0.998 for both training and testing datasets. Since the efficiency is found out to be much less sensitive to the number of inlet particles, the correlation is harnessed to derive an averaged expression for the efficiency as a function of the inlet velocity and particles density. It acquires R2 > 0.999, demonstrating excellent accuracy of the function, which can be used for practical purposes. However, a shorter correlation is also derived with R2 > 0.98 for stronger interpretation.

• Publication year

  2026

• Venue

  Scientific Reports

• Publication date

  2026-01-09

• Fields of study

  Medicine, Materials Science, Engineering

• Identifiers
  DOI 10.1038/s41598-025-34450-0PMID 41513704PMCID 12864997
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Recent progress in biopolymer-based electrospun nanofibers and their potential biomedical applications: A review.

  2025cited by this paper
• Three dimensional modeling of filtration process in complex filter structures using a data-free physics-informed neural network coupled with smoothed particle hydrodynamic

  2025cited by this paper
• CFD-Based Optimization of Dynamic Cyclones with Variable Vortex Length Using GMDH Artificial Neural Network

  2025cited by this paper
• Thermo-hydrodynamic analysis of various curved solar air-heaters with boot-shaped ribs: CFD simulations coupled with an optimized Artificial Neural Network model

  2025cited by this paper
• An improved simulation methodology for nanoparticle injection through aerodynamic lens systems

  2025cited by this paper
• Novel exact solutions of momentum and energy equations for hybrid nanofluid flow on a stretching sheet: Whittaker’s function-based solutions

  2025cited by this paper
• Application of machine learning models for predicting membrane permeability under different manufacturing and operational conditions

  2025influential reference
• Dye-cleaning prediction with a variant of nature-inspired algorithms coupled with extreme gradient boosting

  2025influential reference
• Field synergy analysis of conjugate heat transfer in nanofluid-filled wavy microchannel heat sink using DPM and DDPM approach

  2025cited by this paper
• The pressure drop of fibrous surface filters for gas Filtration: Modeling and experimental studies

  2024cited by this paper
• Mean-line analysis and optimal design of turbines using a proper algorithm for choked conditions

  2024cited by this paper
• Machine learning applications for electrospun nanofibers: a review

  2024cited by this paper
• Machine learning-assisted performance prediction from the synthesis conditions of nanofiltration membranes

  2024cited by this paper
• Heat transfer and erosion control of nanofluid flow with tube inserts: Discrete phase model and adaptive neuro-fuzzy inference system approach

  2024cited by this paper
• Numerical Model of Filtration Efficiency Based on Fractal Characteristics of Particulate Matter and Particle Filter

  2023cited by this paper
• Modeling and optimization of the core-shell nanofibrous composite mat as a scaffold via hybrid models

  2022cited by this paper
• Ultrafine and bimodal structured polyamide-6 nanofiber/nets membrane for air nanofiltration

  2022cited by this paper
• Machine-based learning of predictive models in organic solvent nanofiltration: Pure and mixed solvent flux

  2020cited by this paper
• Modeling and design optimization for pleated membrane filters

  2019cited by this paper
• Aerosol-radiation interaction in atmospheric models: Idealized sensitivity study of simulated short-wave direct radiative effects to particle microphysical properties

  2018cited by this paper
• On the developments of Darcy's law to include inertial and slip effects

  2017cited by this paper
• Numerical Heat Transfer And Fluid Flow

  2016cited by this paper
• Multiphase Flows with Droplets and Particles

  2011cited by this paper
• Distilling Free-Form Natural Laws from Experimental Data

  2009cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition

  2009cited by this paper
• Procedure for Estimation and Reporting of Uncertainty Due to Discretization in CFD Applications

  2007influential reference
• An effective screening design for sensitivity analysis of large models

  2007cited by this paper
• Computational study of a single‐phase flow in packed beds of spheres

  2005cited by this paper
• Microflows and Nanoflows

  2005cited by this paper
• A Simple Mesh Generator in MATLAB

  2004cited by this paper
• Inertial flow structures in a simple‐packed bed of spheres

  2003cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

  2001cited by this paper
• Aerosol Technology Properties, Behavior, and Measurement of Airborne Particles

  2000cited by this paper
• Aerosol particle deposition in an obstructed turbulent duct flow

  1994cited by this paper
• Two-equation eddy-viscosity turbulence models for engineering applications

  1994cited by this paper
• Genetic Programming: On the Programming of Computers by Means of Natural Selection

  1992cited by this paper
• Dispersion and Deposition of Spherical Particles from Point Sources in a Turbulent Channel Flow

  1992cited by this paper
• Factorial sampling plans for preliminary computational experiments

  1991cited by this paper
• Aerosol Technology: Properties, Behavior, and Measurement of Airborne Particles

  1982cited by this paper
• Re-evaluation of millikan's oil drop data for the motion of small particles in air

  1982cited by this paper
• Applied Regression Analysis

  1968cited by this paper

• No citing papers are available for this paper.