Zhiwei Li, Ph.D. (李志伟 博士)

Research Assistant Professor, The Hong Kong Polytechnic University

Dr. Zhiwei Li

Office: ZN613, Block Z, PolyU, HK

Email: zhiwei.li@polyu.edu.hk

I am currently a Research Assistant Professor in the Department of Land Surveying and Geo-Informatics (LSGI) at The Hong Kong Polytechnic University (PolyU). I am also affiliated with the PolyU JC STEM Lab of Earth Observations (POLEIS) and the Research Centre for Artificial Intelligence in Geomatics (RCAIG), both led by Prof. Qihao Weng.

My research primarily focuses on Remote Sensing of Cloudy and Rainy Environments, leveraging big Earth observation data and GeoAI to tackle environmental and climate change challenges, particularly in tropical and subtropical regions with frequent cloud cover and heavy rainfall. The specific research topics include environmental remote sensing, cloud detection and removal, multi-source data fusion, land cover/use mapping, flood monitoring. I have authored over 20 journal papers in RSE, ISPRS P&RS, IEEE TGRS, etc., with a total of over 2500 citations (as of September 2024 in Google Scholar), among which four have been selected as 🏆ESI Highly Cited Papers.

I obtained my Ph.D. degree in Cartography and Geoinformation Engineering from Wuhan University in June 2020 under the supervision of Prof. Huanfeng Shen and Prof. Zongyi He. Prior to my current position, I worked as a Postdoctoral Fellow at Wuhan University from July 2020 to June 2022. I have been the PI of one project funded by the National Natural Science Foundation of China (NSFC) and two projects funded by the China Postdoctoral Science Foundation. The methods and tools I developed have been widely applied to generate national or regional remote sensing data products and to support national land resource monitoring by the China Land Survey and Planning Institute and other related departments.

News

Sep 23, 2024 Our recent Seamless Flood Mapping paper has been selected by NASA Landsat Science as one of the ‘Select Landsat Publications’ for October 2024! 🛰️🌏 (Link)
Citation: Li, Z., Xu, S., Weng, Q., 2024. Beyond clouds: Seamless flood mapping using Harmonized Landsat and Sentinel-2 time series imagery and water occurrence data. ISPRS Journal of Photogrammetry and Remote Sensing, 216, 185-199. (PDF)
Aug 4, 2024 Our new paper entitled Beyond clouds: Seamless flood mapping using Harmonized Landsat and Sentinel-2 time series imagery and water occurrence data has been published in ISPRS Journal of Photogrammetry and Remote Sensing (HTML, PDF, Code).
Research Spotlight💡: We developed SeamlessFloodMapper for seamless flood mapping using optical satellite image time series, overcoming cloud cover limitations. Evaluated with Harmonized Landsat and Sentinel-2, it maps floods seamlessly at a 2–3 day interval and 30 m resolution, supporting effective flood monitoring and disaster management.
Jul 10, 2024 I presented our recent study on flood mapping at the 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) and received a lot of attention (Link).
Zhiwei Li, Shaofen Xu, Qihao Weng, 2024. Can we reconstruct cloud-covered flooding areas in harmonized Landsat and Sentinel-2 image time series?, IEEE International Geoscience and Remote Sensing Symposium (IGARSS). pp. 3686-3688. Athens, Greece. (PDF, Poster)
Jun 24, 2024 I co-chaired a session titled ‘Applications of Geospatial Techniques in Urban Environments’ at the Asia Oceania Geosciences Society (AOGS) 21st Annual Meeting (AOGS 2024) with Dr. Cheolhee Yoo (Link).
May 10, 2024 Congratulations to MSc student Huan ZHOU on successfully completing the oral presentation of his dissertation entitled “Unlocking the Potential of Multi-Modal Self-Supervised Learning for Flood Inundation Mapping”.:clap::tada:
May 5, 2024 Our new paper entitled Learning spectral-indices-fused deep models for time-series land use and land cover mapping in cloud-prone areas: The case of Pearl River Delta has been published in Remote Sensing of Environment (HTML, PDF).
Research Spotlight💡: An integrated time series mapping method enhances LULC accuracy and frequency in cloud-prone areas using spectral-indices-fused deep learning models and reconstruction techniques. The assessment shows variations in accuracy with different cloud masks, highlighting their importance in LULC mapping. (PAIR News, Blog, WeChat Article)