Results 121 to 130 of about 8,116 (238)
Theoretical and Applied Mechanics LettersDynamic wake field information is vital for the optimized design and control of wind farms. Combined with sparse measurement data from light detection and ranging (LiDAR), the physics-informed neural network (PINN) frameworks have recently been employed ...
Junyong Song +3 more
doaj +1 more source
Journal of Applied Clinical Medical Physics, Volume 27, Issue 11, November 2026.Abstract Background Carbon ion radiotherapy (CIRT) offers superior dose conformity and biological effectiveness; however, its precision is highly sensitive to respiratory motion, leading to dose uncertainty and interplay effects that compromise treatment accuracy.
Jianhua Ding, Peng Li, Chai Hong Yeong
wiley +1 more source
Advanced Materials, Volume 38, Issue 61, 2 November 2026.Water harvesting, radiative cooling, and interfacial solar evaporation are fundamentally governed by coupled heat, mass, and light transport processes. These processes are mediated by pore architecture, including pore size, connectivity, and hierarchical organization.
Dejan J. Trajkovski +5 more
wiley +1 more source
GAMM-Mitteilungen, Volume 49, Issue 4, November 2026.Abstract In mechanics of materials, many powerful methods are accessible only to experts. Constitutive models, for example, describe the relation between stress and strain in materials and are a core ingredient of simulations from structural engineering to biomechanics. Yet building and using such models requires specialized expertise—a barrier for the
Marius Tacke +4 more
wiley +1 more source
Small Science, Volume 6, Issue 11, November 2026.This article presents a comprehensive framework for the AI‐guided photocorrosion inhibition of III–V photoelectrodes. It explores how machine learning accelerates material discovery through targeted strategies in AI‐guided composition, passivation, and growth.
Nafeesa Sarfraz +5 more
wiley +1 more source
Physics-informed neural network (PINN) had been proved to be an effective tool for solving partial differential equations and systems of equations. We used the PINN algorithm to obtain the numerical solution of the 1+1-dimensional KdV-mKdV equation, and ...
栗雪娟(LI Xuejuan) +1 more
core +1 more source
Journal of Food Process Engineering, Volume 49, Issue 11, November 2026.A compact multispectral imaging system combined with a physics‐informed neural network enables real‐time quantitative monitoring and prediction of enzymatic browning in fresh‐cut apples. The Weibull‐constrained model improves temporal extrapolation over conventional Weibull and data‐driven neural network approaches.
Guojun Tang +2 more
wiley +1 more source
Research on SCO2 Critical Flow Prediction Model Based on PINN-HEM Hybrid Framework
Yuanzineng kexue jishuThe accurate prediction of critical flow in supercritical carbon dioxide (SCO2) reactor systems is a crucial aspect of pressure drop accident safety analysis.
WANG Xinyu1, WANG Siyuan1, YANG Jun2, CHEN Lilian1, LYU Junhong1, ZHANG Xuan1, KANG Yanjie1, YUAN Yuan1, ZHOU Yuan1
doaj +1 more source
Understanding the Difficulty of Solving Cauchy Problems with PINNs
CoRRPhysics-Informed Neural Networks (PINNs) have gained popularity in scientific computing in recent years. However, they often fail to achieve the same level of accuracy as classical methods in solving differential equations. In this paper, we identify two sources of this issue in the case of Cauchy problems: the use of $L^2$ residuals as objective ...
Tao Wang +3 more
openaire +3 more sources