罗玖

发布时间:2026-01-13浏览次数:1869

主要研究方向

1. 深度学习与科学计算

2. 智能仿真与工业数字孪生

3. 数学建模与高性能计算

4. 复杂系统参数反演方法

5. 人工智能驱动新材料设计



亮点工作介绍

团队采用机理与数据融合的数学建模方法、高通量计算、人工智能结合全局优化等方法,展开复杂工业过程多尺度智能设计,攻关绿色低碳膜法水处理技术。系列成果发表于Nature旗下npj Clean Water》(IF=11.4)与《Communications Engineering、《Science Bulletin》(IF=21.1)、Desalination》(IF=9.8)、Separation and Purification Technology(IF=9.0)高水平期刊,并两次获得国家超级计算广州中心宣传报道。

1.发表在《npj Clean Water》(2025)上的论文原文:

https://www.nature.com/articles/s41545-025-00491-1


2.发表在《Separation and Purification Technology》(2025)上的论文原文:

Fast solution of 3D transport processes using a physics-informed neural network with embedded transfer learning - ScienceDirect


3. 发表在《Communications Engineering》(2025)上的论文原文:

Holomorphic embedding method for large-scale reverse osmosis desalination optimization | Communications Engineering (nature.com)


4.发表在《npj Clean Water》(2024)上的论文原文:

Bio-inspired design of next-generation ultrapermeable membrane systems | npj Clean Water (nature.com)


5. 发表在《Communications Engineering》(2024)上的论文原文:

A rapid-convergent particle swarm optimization approach for multiscale design of high-permeance seawater reverse osmosis systems | Communications Engineering (nature.com)


6. 发表在Science Bulletin》(2023)上的论文原文

Supercomputing and machine learning-aided optimal design of high permeability seawater reverse osmosis membrane systems - ScienceDirect

"HPC+AI for Science新范式,加速先进反渗透系统多尺设计"(2023)



7. 发表在Desalination》(2020)上的论文原文:

A hybrid modeling approach for optimal design of non-woven membrane channels in brackish water reverse osmosis process with high-throughput computation - ScienceDirect

向海洋要淡水!广州超算研究团队推动反渗透膜组件优化设计(2020)