.png){kind=icon}
返回
Deep learning-based surrogate modeling for underground hydrogen storage
.png){kind=icon}
PRE
AI
DOI：10.1016/j.advwatres.2025.105014.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• 我们采用Swin-Unet进行地下氢气存储的代理建模。
• Swin-Unet能够实现储层压力和氢饱和度时空演化的准确且高效的预测。
• 与U-Net和Segmentation Transformer相比，Swin-Unet提高了压力预测精度并降低了饱和度训练成本。
期刊
IF:
4.2
论文数:
4.6K
被引数:
1.5W
机构
暂无机构信息
引用论文
Deep Convolutional Encoder‐Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media深度卷积编码器-解码器网络，用于对异质介质中的动态多相流进行不确定性量化
OAAI
OAAI分享收藏Assessment of feasible strategies for seasonal underground hydrogen storage in a saline aquifer评估盐水含水层中季节性地下储氢的可行策略
PREAI
分享收藏Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers从序列到序列的角度重新思考语义分割
OAAI
OAAI分享收藏分享收藏分享收藏Subsurface Microbial Hydrogen Cycling: Natural Occurrence and Implications for Industry.png)
MICROORGANISMSOAAI
MICROORGANISMSIF4.2
OAAI分享收藏A critical review of underground hydrogen storage: From fundamentals to applications, unveiling future frontiers in energy storage地下储氢的批判性回顾: 从基础到应用，揭示储能的未来前沿
PREAI
分享收藏Review of reservoir challenges associated with subsurface hydrogen storage and recovery in depleted oil and gas reservoirs与枯竭油气藏地下氢储存和开采相关的储层挑战综述
PREAI
分享收藏
查看更多内容