Qingsong Xu

Tel: +4917674948438
Room:  221 (TUM Ottorbunn)
E-mail: qingsong.xu(at)tum.de
More information:

Google Scholar
GitHub
ResearchGate

 

Curriculum Vitae

  • Since 02.2022, Ph.D. Candidate, Technical University of Munich, Germany
  • 2021.8-2022.1, Visiting student, Westlake University, China
  • 2018.8 – 2021.6, Master Degree, Geotechnical Engineering, University of Chinese Academy of Sciences, China
  • 2014.6 - 2018.8, Bachelor Degree, Geotechnical Engineering, Chengdu University of Technology, China

Research Topic

  • Global/regional disaster (extreme climate, floods, earthquakes) assessment and temporal-spatial prediction
  • Physics-informed machine learning, physical model simulation with machine learning, and graph neural networks
  • Unsupervised/few-shot learning, domain adaptation, meta-learning
  • Remote sensing image perceptions and dynamic cognitions for  hydrologic process

Awards

  • National Scholarship for Postgraduate Students
  • Outstanding graduate and excellent graduation thesis
  • The Gold Award for "Geology+" Innovation and Entrepreneurship,  the Silver Award for "Internet +" Innovation and Entrepreneurship

Key publications

  • Xu Q, Ouyang C, Jiang T, et al. MFFENet and ADANet: a robust deep transfer learning method and its application in high precision and fast cross-scene recognition of earthquake-induced landslides[J]. Landslides, 2022: 1-31.
  • Xu Q, Yuan X, Ouyang C. Class-aware domain adaptation for semantic segmentation of remote sensing images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 60: 1-17.
  • Xu Q, Yuan X, Ouyang C, et al. Attention-based pyramid network for segmentation and classification of high-resolution and hyperspectral remote sensing images [J]. Remote Sensing, 2020, 12(21): 3501.