Bai Aijuan

Mrs. Bai Aijuan


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 January 2025 in Atmosphere
Verified
Journal Article
Open access
PDF file
BABai Aijuan
Bai Aijuan
JBJinfeng Bai
Jinfeng Bai
ZWZhao Wang
Zhao Wang
TCTu Chaoyong
Tu Chaoyong
This study investigated the source, trajectory, and precipitation of the Southwest (SW) vortex, which was linked with the Plateau (P) vortex. Based on the statistical study of a number of cases, this study showed the following results. The SW vortex tended to originate at the northeastern and western peripheries of the Sichuan Basin, normally coinciding with the presence of the P vortices in the eastern region of the Tibetan Plateau. Most of the aforementioned vortices exhibited a longer life span, and resulted in severe storms averaging approximately 50 mm of rainfall per day, especially in the cases of more than 100 mm of rainfall per day in eastern and southern China. Furthermore, new findings were obtained: (1) The SW vortex and the P vortex were attributed from an ‘Ω’ circulation pattern from blocking high in middle to high latitudes region. The SW vortex was notably influenced by the convergence of two air currents. In the lower troposphere, the southwesterly jet of the South Asian monsoon flowed over and around the Yungui Plateau, and cold–dry air from the north flowed into the Basin. (2) Both the SW vortex and the P vortex displayed a shallow synoptic system characterized below 500 hPa, and wet–cold cores formed around the sources at low altitudes. (3) The analysis on atmospheric instability and dynamics suggested that the vortices’ eddies generated significant convective instability at lower levels. The circulation pattern and instability conditions facilitated the heavy precipitation associated with the SW vortex, and the ample water vapor and subsequent latent heat intensified the precipitation.

12 July 2015 in Theoretical and Applied Climatology
Verified
Journal Article
Closed access
PDF file
BABai Aijuan
Bai Aijuan
LGLi Guoping
Li Guoping

6 September 2024 in Atmosphere
Verified
Journal Article
Open access
PDF file
JGJianhong Gan
Jianhong Gan
TLTao Liao
Tao Liao
YQYouming Qu
Youming Qu
BABai Aijuan
Bai Aijuan
PWPeiyang Wei
Peiyang Wei
THTongli He
Tongli He
Changes in the jet stream not only affect the persistence of climate change and the frequency of extreme weather but are also closely related to climate change phenomena such as global warming. The manual way of drawing the jet stream axes in meteorological operations suffers from low efficiency and subjectivity issues. Automatic identification algorithms based on wind field analysis have some shortcomings, such as poor generalization ability, and it is difficult to handle merging and splitting. A semi-supervised learning jet stream axis identification method is proposed combining consistency learning and self-training. First, a segmentation model is trained via semi-supervised learning. In semi-supervised learning, two neural networks with the same structure are initialized with different methods, based on which pseudo-labels are obtained. The high-confidence pseudo-labels are selected by adding perturbation into the feature layer, and the selected pseudo-labels are incorporated into the training set for further self-training. Then, the jet stream narrow regions are segmented via the trained segmentation model. Finally, the jet stream axes are obtained with the skeleton extraction method. This paper uses the semi-supervised jet stream axis identification method to learn features from unlabeled data to achieve a small amount of labeled data to effectively train the model and improve the method’s generalization ability in a small number of labeled cases. Experiments on the jet stream axis dataset show that the identification precision of the presented method on the test set exceeds about 78% for SOTA baselines, and the improved method exhibits better performance compared to the correlation network model and the semi-supervised method.