.png){kind=icon}
.png){kind=icon}
Return
Magnesium-ion battery cathode materials: Artificial intelligence applications, research advances, and industrialization
.png){kind=icon}
OA
AI
Z
L
G
S
N
X
J
X
F
DOI：10.1016/j.jma.2026.102211.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Highlights the transformative role of AI in screening, predicting, and analyzing Mg-ion battery cathodes. • Systematically evaluates cathode materials’ structure, mechanisms, modification strategies, and performance. • Elucidates the intrinsic challenges of Mg2+ as the root cause limiting cathode performance. • Summarizes industrialization progress and outlines future directions for high-performance cathode design. • Provides a comprehensive reference to bridge fundamental research and industrial development.
Keywords:
Magnesium-ion battery
Cathode material
Artificial intelligence
Machine learning
Industrialization
CEI
cathode-electrolyte interphase
DFT
density functional theory
AIMD
ab initio molecular dynamics
RNN
recurrent neural networks
FCNN
fully connected neural networks
CGCNN
crystal graph convolutional neural networks
MAE
mean absolute error
NequIP
neural equivariant interatomic potentials
SVR
support vector regression
DNN
deep neural networks
SVM
support vector machines
KRR
kernel ridge regression
GNN
graph neural networks
CDVAE
crystal diffusion variational autoencoder
GAT
graph attention networks
MHA-ResNet
multi-head attention and residual networks
TRL
technology readiness level
Journal
IF:
13.8
Papers:
2.1K
Citations:
1.6W
Organization
Cited Papers