Han's Homepage

Han Wang

Atmosphere · Wind Power · Scientific ML

Ph.D. · HKUST · 2025 BSc · HHU · 2021

I'm a Postdoctoral Researcher (CORE Fellowship awardee) at HKUST, working with Prof. Hui Su at the intersection of AI and Earth science. Before this, I completed my Ph.D. at HKUST in 2025 with Prof. Jiachuan Yang. Outside research, I enjoy hiking , photography , time by the sea and scuba diving .

Clear Water Bay · Loading weather… (Open-Meteo estimate)

Our weather playground ↗

Han Wang at a research desk overlooking Clear Water Bay through a glass curtain wall, with weather dice on a mountainous Hong Kong relief map

Research focus

I build scientific machine learning models for complex environmental systems. My work began with urban climate prediction and now brings spatiotemporal modeling and Graph Neural Networks (GNNs) to wind and renewable energy forecasting. I also use generative models to simulate catastrophic events. I believe AI will reshape how we conduct science and understand the world.

Scientific ML

Turning physics-aware deep learning into practical forecasting tools under sparse observations, domain shifts, and real-world uncertainty.

Urban climate

Tracing how urban form, vegetation, and synoptic forcing shape canopy-layer temperature dynamics, the physical foundation of my earlier work.

Wind and renewable energy

Bringing those spatiotemporal ideas into wind power and broader renewable forecasting, with an eye toward cleaner and more reliable energy systems.

Selected works

  1. 2026
    Leveraging atmospheric information across scales for local temperature forecasting using a novel multi-scale perception network. Wang, H., Chen, Y., & Yang, J. Journal of Geophysical Research: Machine Learning and Computation, 3, e2025JH001083. doi:10.1029/2025JH001083
  2. 2026
    Intra-city scale graph neural networks enhance short-term air temperature forecasting. Wang, H., Tang, J., Zhang, J., & Yang, J. Atmospheric Chemistry and Physics, 26(2), 947–961. doi:10.5194/acp-26-947-2026
  3. 2024
    Time-series forecasting of pedestrian-level urban air temperature by LSTM: Guidance for practitioners. Wang, H., Zhang, J., & Yang, J. Urban Climate, 56, 102063. doi:10.1016/j.uclim.2024.102063
  4. 2023
    Machine learning applications on air temperature prediction in the urban canopy layer: A critical review of 2011–2022. Wang, H., Yang, J., Chen, G., Ren, C., & Zhang, J. Urban Climate, 49, 101499. doi:10.1016/j.uclim.2023.101499

Referee service

Reviewer for: Geophysical Research Letters, Environmental Research Letters, Urban Climate, Sustainable Cities and Society, Advances in Atmospheric Sciences, and Meteorological Applications. IOP Trusted Reviewer, IOP Publishing (2026).

Contact