Physics-Informed Machine Learning for Microscale Drying of Plant-Based Foods: A Systematic Review of Computational Models and Experimental Insights
This review examines the current state of research on microscale cellular changes during the drying of plant-based food materials (PBFM), with particular emphasis on computational modelling approaches. The review addresses the critical need for advanced computational methods in microscale investigations. We systematically analyse experimental studies in PBFM drying, highlighting their contributions and limitations in capturing cellular-level phenomena, including challenges in data acquisition and measurement accuracy under varying drying conditions. The evolution of computational models for microstructural investigations is thoroughly examined, from traditional numerical methods to contemporary state-of-the-art approaches, with specific focus on their ability to handle the complex, nonlinear properties of plant cellular materials. Special attention is given to the emergence of data-driven models and their limitations in predicting microscale cellular behaviour during PBFM drying, particularly addressing challenges in dataset acquisition and model generalization. The review provides an in-depth analysis of Physics-Informed Machine Learning (PIML) frameworks, examining their theoretical foundations, current applications in related fields, and unique advantages in combining physical principles with neural network architectures. Through this comprehensive assessment, we identify critical gaps in existing methodologies, evaluate the trade-offs between different modelling approaches, and provide insights into future research directions for improving our understanding of cellular-level transformations during PBFM drying processes. The review concludes with recommendations for integrating experimental and computational approaches to advance the field of food preservation technology.
Code (0)
등록된 구현이 없습니다.
Tasks
Physics-informed machine learningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations
Multiscale problems are ubiquitous in physics. Numerical simulations of such problems by solving partial differential equations (PDEs) at high resolution are computationally too expensive for many-query scenarios, e.g., …
Operator learningUncertainty QuantificationData-driven modeling of Landau damping by physics-informed neural networks
Kinetic approaches are generally accurate in dealing with microscale plasma physics problems but are computationally expensive for large-scale or multiscale systems. One of the long-standing problems in plasma physics is…
Extracting particle size distribution from laser speckle with a physics-enhanced autocorrelation-based estimator (PEACE)
Extracting quantitative information about highly scattering surfaces from an imaging system is challenging because the phase of the scattered light undergoes multiple folds upon propagation, resulting in complex speckle …
BIG-bench Machine LearningHybrid machine learning based scale bridging framework for permeability prediction of fibrous structures
This study introduces a hybrid machine learning-based scale-bridging framework for predicting the permeability of fibrous textile structures. By addressing the computational challenges inherent to multiscale modeling, th…
Computational EfficiencyHybrid Machine LearningA Neural Operator based Hybrid Microscale Model for Multiscale Simulation of Rate-Dependent Materials
The behavior of materials is influenced by a wide range of phenomena occurring across various time and length scales. To better understand the impact of microstructure on macroscopic response, multiscale modeling strateg…