Results 191 to 200 of about 18,341 (302)

Machine Learning Accelerated Computational Design of Bio‐Inspired Catalysts in the Nitrogen Reduction Reaction

Advanced Materials, EarlyView.
We introduce a computational workflow that combines quantum chemical calculations and machine learning techniques to predict the catalytic performance of a wide range of catalysts in the nitrogen reduction reaction (NRR). The analysis of the trained models provides insights into the complex structure–activity relationship in experimental catalytic ...
Leonardo Di Ciano, Zihan You, Haoran Chen, Qifan Zhong, Rong‐Zhen Liao, Shaoqi Zhan   +5 more
wiley   +1 more source

Collocation-based Robust Variational Physics-Informed Neural Networks (CRVPINN)

Physics-Informed Neural Networks (PINNs) have been successfully applied to solve Partial Differential Equations (PDEs). Their loss function is founded on a strong residual minimization scheme.
Łoś, Marcin, Maczuga, Paweł, Vilkha, Askold, Służalec, Tomasz, Paszyński, Maciej, Uriarte, Carlos   +5 more
core  

Low-Temperature Prediction in Commercial Lithium-Ion Batteries during Dynamic Usage via Enhanced Physics-Informed Neural Networks. [PDF]

ACS Omega
Pereira EL, Soares DM.
europepmc   +1 more source

Deep Learning Inverse Design of Phase‐Change Reconfigurable Terahertz Metadevices for Multidimensional Secure Communication

Advanced Materials, EarlyView.
A deep learning inverse‐design framework is established to create versatile reconfigurable terahertz metadevices. By synergizing deep learning with phase‐change materials, this approach enables on‐demand customization of multidimensional electromagnetic responses.
Yisheng Dong, Xieyu Chen, Aarthy Nagarajan, Yi Yang, Zhihao Wang, Rui Yu, Chuang Zheng, Chunmei Ouyang, Xueqian Zhang, Tun Cao, Ranjan Singh, Zhen Tian   +11 more
wiley   +1 more source

Invariant Physics-Informed Neural Networks for Ordinary Differential Equations

Physics-informed neural networks have emerged as a prominent new method for solving differential equations. While conceptually straightforward, they often suffer training difficulties that lead to relatively large discretization errors or the failure to ...
Valiquette, Francis, Bihlo, Alex, Arora, Shivam   +2 more
core  

Gradient-Driven Physics Informed Neural Networks for Conduction Heat Transfer and Incompressible Laminar Flow. [PDF]

J Comput Nonlinear Dyn
Lu T, Shahadat MRB, Liu Q, He R, Jiang X, Li Z.   +5 more
europepmc   +1 more source

Full Vectorial Field Sensing Using Liquid Crystal Droplet Arrays

Advanced Materials, EarlyView.
An inkjet‐printed liquid crystal droplet array enables compact, low‐cost, single‐shot sensing of the full vectorial light field. Within a single platform, it simultaneously retrieves intensity, polarization, and phase, while dual‐wavelength operation highlights its capability for multi‐wavelength optical field characterization. ABSTRACT Determining the
Xuke Qiu, Jinge Guo, Jiahe Cui, Runchen Zhang, Zimo Zhao, Yifei Ma, Waqas Kamal, Steve J. Elston, Alfonso A. Castrejón‐pita, Stephen M. Morris, Chao He   +10 more
wiley   +1 more source

Parameter calibration method for car-following models under snowy weather conditions: Integrating an informer time series encoder and physics-informed neural networks. [PDF]

PLoS One
Sun Y, Li W, Yang M, Zhang X.
europepmc   +1 more source

Soft Hardware, Flowing Software: Reconfigurable Microfluidics for Adaptable Chemical Computation

Advanced Materials, EarlyView.
A reconfigurable microfluidic platform based on soft, photo‐printable, and chemically erasable hydrogel structures printed and erased in situ is used to control flow routing, mixing, chemical patterning, and even chemical computing. Using hardware to control chemical computations decouples logic function from molecular composition, demonstrated via ...
Piet J. M. Swinkels, Brigitta Dúzs, Oliver Skarsetz, Kohei Nishiyama, Andreas Walther   +4 more
wiley   +1 more source

Investigating the use of physics informed neural networks for dam-break scenarios. [PDF]

PLoS One
Mumtaz K, Nadeem MW, Khan A, Lakdawala Z.   +3 more
europepmc   +1 more source