Kuai Dai   代快

Postdoctoral Fellow

Department of Civil and Environmental Engineering
Hong Kong University of Science and Technology (HKUST)
Clear Water Bay, Kowloon, Hong Kong

Email: dkuaiatustdothk

[Github]   [Google Scholar]

Kuai Dai

About Me

I am currently a Postdoctoral Fellow in the Department of Civil and Environmental Engineering at the Hong Kong University of Science and Technology, supervised by Prof. Hui Su. My research focuses on interdisciplinary AI-for-Science research, with particular emphasis on weather nowcasting and climate modeling, as well as wind and solar energy resource assessment and applications.

I obtained my Ph.D. degree in Computer Science from the Harbin Institute of Technology (Shenzhen), under the supervision of Prof. Xutao Li. I actively serve as a reviewer for over 20 leading international journals and top-tier AI conferences.

News

▶ Show older news...
  • [2024.09.20] The paper and source codes of DDMS [PDF] is updated [CODE].
  • [2024.06.25] The pretrained model and source codes of DDMS is available.
  • [2024.04.24] The pretrained model and source codes of STCNet [PDF] is available [CODE].
  • [2024.04.16] One paper titled Four-hour thunderstorm nowcasting using deep diffusion models of satellite is submitted to [arXiv].
  • [2024.04.04] The pretrained model and source codes of MSTCGAN [PDF] is available [CODE].
  • [2024.02.27] One co-author paper is accepted by CVPR 2024.
  • [2024.01.22] One academic contribution honor is awarded by ICES (Shenzhen).
  • [2024.01.22] Team entertainment activities of ICES Lab to OCT East & Dameisha Seaside Park.
  • [2023.12.23] One paper is accepted by TOMM.
  • [2023.08.07] One paper is accepted by TGRS.
  • [2023.07.31] Team entertainment activities of ICES Lab to Shenzhen Observatory.
  • [2023.07.24] One paper is accepted by TCSVT.
  • [2023.07.09] A special activity of HIT PHD for Chongqing (2023.07.09~2023.07.14).
  • [2022.06.04] One paper is accepted by TGRS.

Research Domain

  • AI for Science: Interdisciplinary research on AI methodologies for meteorological remote sensing, weather and climate modeling, and clean energy applications.

  • Satellite Big Data Mining: Large-scale satellite observation data analysis, representation learning, and knowledge discovery, with spatiotemporal predictive learning as a core methodological component.
  • Selected Publications

    Journal Papers

    Four-hour thunderstorm nowcasting using a deep diffusion model of satellite data.

    Kuai Dai, Xutao Li*, Junying Fang, Yunming Ye*, Demin Yu, Hui Su, Di Xian, Danyu Qin, Jingsong Wang*.

    Learning spatial-temporal consistency for satellite image sequence prediction.

    Kuai Dai, Xutao Li*, Chi Ma, Shenyuan Lu, Yunming Ye, Di Xian, Lin Tian, Danyu Qin.

    MSTCGAN: Multiscale time conditional generative adversarial network for long-term satellite image sequence prediction.

    Kuai Dai, Xutao Li*, Yunming Ye, Shanshan Feng, Danyu Qin, Rui Ye.

    Conference Papers

    SatSolarCast: A Flexible Framework for Multimodal Solar Irradiance Forecasting via Memory-Alignment Learning.

    Kuai Dai, Hui Su*, Chengxing Zhai, Huiwei Lin, Mingliang Bai.

    Efficient Forecasting of Geostationary Infrared Brightness Temperature Sequences: A Benchmark and a Lightweight Model.

    Kuai Dai, Hui Su*, Xutao Li, Chengxing Zhai.

    DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting.

    Demin Yu, Xutao Li*, Yunming Ye, Baoquan Zhang, Chuyao Luo, Kuai Dai, Rui Wang, Xunlai Chen.

    Honors and Awards

  • Outstanding Ph.D. Dissertation, Harbin Institute of Technology (Top 3%), 2024.
  • Academic Services

    Reviewer for Academic Journals: Program Committee Member for AI Conferences:

    Work Experience

  • Postdoctoral Fellow at HKUST CIVL Department, 2024.11 - Now.
    Interdisciplinary research at the intersection of AI, weather & climate, and clean energy.
  • Statistics