个人简介

博士毕业于华东师范大学，拥有数学、统计学、地理学、计算机科学等交叉背景，在读期间曾赴哥伦比亚大学“应用数学”专业进行博士联合培养，后于中山大学“大气科学”专业从事博士后研究，目前为深圳技术大学人工智能学院助理教授、硕导。目前主持在研包括国家级、省部级等多项科研项目，并参与在研1项科技部重点研发计划。累计发表SCI期刊论文多篇，获多项国家发明专利。主要研究方向包括：人工智能气象预报、地学大数学建模及气象灾害风险分析等。

研究兴趣

将地学多源大数据（包括卫星遥感、雷达观测、数值模式与地面观测等）与领域先验物理知识深度融合，以人工智能技术为核心驱动，采用“理论驱动与数据驱动”相结合的建模范式，系统研发具有“数据-知识”耦合特性的气象预报模型。研究重点涵盖人工智能可解释性（XAI）、物理约束下的深度学习等方法，推动人工智能在科学研究（AI for Science, AI4S）中的深入应用。成果具体应用于短临降水预报、台风路径与强度预测、生态农业气象服务、自然灾害气象预警等关键领域，提升预报精度与决策支持能力。

代表性论文（一作/通讯）

[1] Rising atmospheric CO2 outweighs elevated vapor pressure deficit in explaining increased intrinsic water use efficiency in Chinese pine (2026). Frontiers in Plant Science, 17: 1721057. https://doi.org/10.3389/fpls.2026.1721057

[2] Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning (2024). Remote Sensing. https://doi.org/10.3390/rs16020275

[3] Estimating tropical cyclone intensity via deep learning and storm morphology recognition from satellite imagery (2025). IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/TGRS.2025.3625624

[4] Similar growth variability in natural and planted forests of Chinese pine (2026). Annals of Forest Science.

[5] Deep learning model based on multi-scale feature fusion for precipitation nowcasting (2024). Geoscientific Model Development. https://doi.org/10.5194/gmd-17-53-2024

[6] TSRC: A Deep Learning Model for Precipitation Short-Term Forecasting over China Using Radar Echo Data (2023). Remote Sensing. https://doi.org/10.3390/rs15010142

[7] Tropical Cyclone Intensity Estimation Using Himawari-8 Satellite Cloud Products and Deep Learning (2022). Remote Sensing. https://doi.org/10.3390/rs14040812

[8] Projected changes of typhoon intensity in a regional climate model: Development of a machine learning bias correction scheme (2021). International Journal of Climatology.

https://doi.org/10.1002/joc.6987

[9] Western North Pacific tropical cyclone track forecasts by a machine learning model (2020). Stochastic Environmental Research and Risk Assessment.

https://doi.org/10.1007/s00477-020-01930-w

[10] A prediction scheme of tropical cyclone frequency based on lasso and random forest (2018). Theoretical and applied climatology. https://doi.org/10.1007/s00704-017-2233-3s

发明专利

[1] 谭金凯. 一种基于点云体素的台风定强方法,系统,设备及介质: CN114049545A[P]. 2022.

[2] 谭金凯, 陈生. 一种台风中心位置偏移量生成方法及台风中心定位方法: CN114550007A[P]. 2022.

[3] 谭金凯. 基于变分自编码的台风云图外推方法、系统、设备和介质: CN115661277B[P]. 2023.

联系方式

如果您在某一领域有新颖的idea，比如XAI、AI4S，我愿意与您共同学习。欢迎报考！

邮箱：tanjinkai@sztu.edu.cn