Shuai Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shuai Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yubao Chen
China Meteorological Administration Meteorological Observation Centre, Beijing 100081, China
2 shared publications - Biao Jiang
College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China
1 shared publication - Haifeng Yu
Huayun Metstar Radar (Beijing) Co., Ltd., Beijing 100094, China
1 shared publication - Hui Wang
Institute of Urban Meteorology, China Meteorological Administration, Beijing 100089, China
1 shared publication - Jianjun Chen
Radar Meteorological Centre, China Meteorological Administration, Beijing 100081, China
1 shared publication - Lu Li
Radar Meteorological Centre, China Meteorological Administration, Beijing 100081, China
1 shared publication
Latest Publications
- Open Access
- 20 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 948
Analysis of Generalization Performance of Tornado Detection Models: A Cross-Domain Evaluation from U.S. to Chinese Weather Radar Observations
Tornadoes pose severe threats, yet their low frequency in China creates a labeled data scarcity that hinders training robust detection models. Leveraging abundant U.S. data offers a solution, though cross-domain generalization remains challenging due to distinct climatic environments and heterogeneous radar systems. This study systematically evaluates the generalization capability of three representative models—TORP, TORP-XGB, and TDA-CNN—trained on the U.S. TorNet dataset and applied to Chinese CINRAD observations (2020–2024) via a zero-shot transfer strategy. The results indicate that while all models demonstrated robust performance in the source domain (with POD values of 0.75, 0.72, and 0.71 for TORP, TORP-XGB, and TDA-CNN, respectively), they experienced varying degrees of performance attenuation in the target domain (with POD values dropping to 0.56, 0.48, and 0.41, respectively). Notably, the TORP model exhibited superior robustness with minimal performance degradation. Further analysis primarily attributes this cross-domain degradation to three factors: disparities in radar systems, magnitude differences in tornado rotational features, and data quality issues. Crucially, sensitivity experiments confirm that linear feature enhancement substantially improves the detection rate and effectively mitigates the cross-domain performance gap, albeit at the cost of increased false alarms. These findings provide a reference for the cross-domain deployment of tornado identification models and future improvements in transfer learning strategies.
- 20 March 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (6) , 948
Open AccessAnalysis of Generalization Performance of Tornado Detection Models: A Cross-Domain Evaluation from U.S. to Chinese Weather Radar Observations
Tornadoes pose severe threats, yet their low frequency in China creates a labeled data scarcity that hinders training robust detection models. Leveraging abundant U.S. data offers a solution, though cross-domain generalization remains challenging due to distinct climatic environments and heterogeneous radar systems. This study systematically evaluates the generalization capability of three representative models—TORP, TORP-XGB, and TDA-CNN—trained on the U.S. TorNet dataset and applied to Chinese CINRAD observations (2020–2024) via a zero-shot transfer strategy. The results indicate that while all models demonstrated robust performance in the source domain (with POD values of 0.75, 0.72, and 0.71 for TORP, TORP-XGB, and TDA-CNN, respectively), they experienced varying degrees of performance attenuation in the target domain (with POD values dropping to 0.56, 0.48, and 0.41, respectively). Notably, the TORP model exhibited superior robustness with minimal performance degradation. Further analysis primarily attributes this cross-domain degradation to three factors: disparities in radar systems, magnitude differences in tornado rotational features, and data quality issues. Crucially, sensitivity experiments confirm that linear feature enhancement substantially improves the detection rate and effectively mitigates the cross-domain performance gap, albeit at the cost of increased false alarms. These findings provide a reference for the cross-domain deployment of tornado identification models and future improvements in transfer learning strategies.
- Open Access
- 4 December 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5624
Weather Radar Parameter Estimation Based on Frequency Domain Processing: Technical Details and Performance Evaluation
Parameter estimation is important in weather radar signal processing. Time-domain processing (TDP) and frequency-domain processing (FDP) are two basic parameter estimation methods used in the weather radar field. TDP is widely used in operational weather radars because of its high efficiency and robustness; however, it must be assumed that the received signal has a symmetrical or Gaussian power spectrum, which limits its performance. FDP does not require assumptions about its power spectrum model and has a seamless connection to spectrum analysis; however, its application performance has not been fully validated to ensure its robustness in an operational environment. In this study, we introduce several technical details in FDP, including window function selection, aliasing correction, and noise correction. Additionally, we evaluate the performance of FDP and compare the performance of FDP and TDP based on simulated and measured weather in-phase/quadrature (I/Q) data. The results show that FDP has potential for operational applications; however, further improvements are required, e.g., windowing processing for signals mixed with severe clutter.
- 4 December 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5624
Open AccessWeather Radar Parameter Estimation Based on Frequency Domain Processing: Technical Details and Performance Evaluation
Parameter estimation is important in weather radar signal processing. Time-domain processing (TDP) and frequency-domain processing (FDP) are two basic parameter estimation methods used in the weather radar field. TDP is widely used in operational weather radars because of its high efficiency and robustness; however, it must be assumed that the received signal has a symmetrical or Gaussian power spectrum, which limits its performance. FDP does not require assumptions about its power spectrum model and has a seamless connection to spectrum analysis; however, its application performance has not been fully validated to ensure its robustness in an operational environment. In this study, we introduce several technical details in FDP, including window function selection, aliasing correction, and noise correction. Additionally, we evaluate the performance of FDP and compare the performance of FDP and TDP based on simulated and measured weather in-phase/quadrature (I/Q) data. The results show that FDP has potential for operational applications; however, further improvements are required, e.g., windowing processing for signals mixed with severe clutter.