刘威，男，1992年10月，特聘副教授，硕士生导师。主要研究方向为海洋电磁勘探技术与装备、人工智能电磁正反演、人工智能矿产预测。主持国家级、省部级及横向合作项目4项；在国内外刊物公开发表  SCI及EI论文10余篇；获发明专利授权1项；湘潭市“小荷”科技创新团队成员。

电子邮件：liuweigoing@126.com

    代表性科研项目

1. 国家自然科学基金青年基金项目（C类），面向跨场景泛化的大地电磁深度学习二维反演基础模型研究，主持，起止时间：2027.01-2029.12

2. 海南省自然科学基金青年基金项目，基于自适应联合监督的大地电磁三维深度学习光滑反演研究，主持，起止时间：2026.03-2028.02

3. 湖南省教育厅科学研究项目，基于物理规律指导的大地电磁深度学习反演研究，主持，起止时间：2024.12-2026.11

4. 青海省重点研发与转化计划项目，基于数据与物理双驱动的AI找矿预测大模型在柴达木盆地及周缘应用研究，核心参与，起止时间：2026.01-2028.12

5.湘潭市“小荷”科技创新团队项目，深海勘探技术与作业装备可靠性研究，核心成员，起止时间：2026-08-2027-07

    代表性授权发明专利

1. 刘威，席振铢，王鹤，等．一种大地电磁的深度学习反演方法及深度学习反演系统．中国发明专利，专利号：ZL202310711844.6

    代表性论文

1． Liu Wei, Wang He, Xi Zhenzhu, Wang Liang, Chen Chaoyang, Guo Tao, Yan Maoshan Wang Tongtong. Multitask Learning-Driven Physics-Guided Deep Learning Magnetotelluric Inversion[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5926416. (SCI)

2． Liu Wei, Wang He, Xi Zhenzhu, Wang Liang. Physics-Informed Deep Learning Inversion with Application to Noisy Magnetotelluric Measurements[J]. Remote Sensing, 2024, 16(1): 62. (SCI)

3． Liu Wei, Wang He, Xi Zhenzhu, Zhang Rongqing. Smooth Deep Learning Magnetotelluric Inversion Based on Physics-Informed Swin Transformer and Multiwindow Savitzky–Golay Filter[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4505214. (SCI)

4． Liu Wei, Wang He, Xi Zhenzhu, Zhang Rongqing, Huang Xiaodi. Physics-Driven Deep Learning Inversion with Application to Magnetotelluric[J]. Remote Sensing, 2022, 14(13): 3218. (SCI)

5． Liu Wei, Xi Zhenzhu, Wang He, Zhang Rongqing. Two-dimensional deep learning inversion of magnetotelluric sounding data[J]. Journal of Geophysics and Engineering, 2021, 18(5): 627-641. (SCI)

6． 刘威, 王鹤, 吴陈子昱, 刘寄仁. 考虑电流型畸变的大地电磁深度学习反演[J]. 中南大学学报(自然科学版), 2026, 1-15. (EI)

7． 王亮, 刘威*, 席振铢, 薛军平, 侯海涛, 龙霞, 王威, 薛文韬. 音频大地电磁与瞬变电磁深度学习联合反演[J]. 地球物理学报, 2024, 67(11): 4372-4384. (SCI, 通讯作者)

8． Wang Liang, Dai Yunfeng, Liu Wei*, Zhou Sheng, Long Xia, Xi Zhenzhu, Xue Junping, Wang Wei. Transient Electromagnetic Investigation of Seawater Intrusion based on Deep Learning Inversion[J]. Journal of Geophysics and Engineering, 2024, 21(6): 1810-1821. (SCI, 通讯作者)

9． Liu Wei, Wang He, Guo Tao, Yan Maoshan, Xi Zhenzhu. Two-dimensional deep learning magnetotelluric inversion[J]. Journal of Physics: Conference Series, 2024, 2895: 012050. (EI)

10． Wang He, Liu Wei, Xi Zhenzhu. Nonlinear inversion for magnetotelluric sounding based on deep belief network[J]. Journal of Central South University, 2019, 26: 2482-2494. (SCI)