Tao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tao Zhang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Chuanying Pan
College of Animal Science and Technology, Northwest A&F University, Yangling, China
1 shared publication - Fangfang Huang
State Key Laboratory of Isotope Geochemistry, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences
1 shared publication - Fengchun Liao
Department of Oral and Maxillofacial Surgery, College of Stomatology, Guangxi Medical University, 10 Shuangyong Road, Nanning, 530021, People's Republic of China
1 shared publication - Hailong Liu
Laoshan Laboratory, Qingdao 266237, China
1 shared publication - Hongzhao Lu
School of Biological Science and Engineering, Shaanxi University of Technology, Hanzhong, China
1 shared publication - Jian Chen
Beijing Institute of Applied Meteorology Beijing China
1 shared publication
Latest Publications
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
A Coupled Transformer–CNN Network: Advancing Sea Surface Temperature Forecast Accuracy
Sea surface temperature (SST) is critically important for understanding ocean dynamics and supporting various marine activities, making accurate short-term SST forecasting highly significant. However, accurately modeling the multi-scale variability of SST remains challenging for existing deep learning (DL) models. This study introduces the Coupled Transformer-CNN Network (CoTCN), a hybrid architecture designed to leverage the multi-scale variability of SST. The CoTCN combines the strengths of Transformers and convolutional neural networks (CNNs), significantly enhancing SST forecasts’ spatial continuity and predictive accuracy. Compared to five state-of-the-art DL models based on Transformer or CNN that include ConvLSTM, ConvGRU, AFNO, PredRNN, and SwinLSTM, CoTCN demonstrates superior performance in global and local areas of SST forecasting. At 1-day lead time, CoTCN reduces the global average root mean square error (RMSE) by over 15%, with forecast errors ranging from 0.20°C to 0.53°C across 1–10 day lead times. Moreover, the CoTCN effectively mitigates the checkerboard artifacts inherent to the Vision Transformer architecture. These findings highlight the effectiveness of CoTCN in capturing SST’s multi-scale features and underscore the promising potential of hybrid architectures for future DL models.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
A Coupled Transformer–CNN Network: Advancing Sea Surface Temperature Forecast Accuracy
Sea surface temperature (SST) is critically important for understanding ocean dynamics and supporting various marine activities, making accurate short-term SST forecasting highly significant. However, accurately modeling the multi-scale variability of SST remains challenging for existing deep learning (DL) models. This study introduces the Coupled Transformer-CNN Network (CoTCN), a hybrid architecture designed to leverage the multi-scale variability of SST. The CoTCN combines the strengths of Transformers and convolutional neural networks (CNNs), significantly enhancing SST forecasts’ spatial continuity and predictive accuracy. Compared to five state-of-the-art DL models based on Transformer or CNN that include ConvLSTM, ConvGRU, AFNO, PredRNN, and SwinLSTM, CoTCN demonstrates superior performance in global and local areas of SST forecasting. At 1-day lead time, CoTCN reduces the global average root mean square error (RMSE) by over 15%, with forecast errors ranging from 0.20°C to 0.53°C across 1–10 day lead times. Moreover, the CoTCN effectively mitigates the checkerboard artifacts inherent to the Vision Transformer architecture. These findings highlight the effectiveness of CoTCN in capturing SST’s multi-scale features and underscore the promising potential of hybrid architectures for future DL models.
- 15 April 2022
- Published by Elsevier in Journal of Genetics and Genomics
- Vol. 49 (11) , 1016-1028
Single-cell RNA-seq analysis of testicular somatic cell development in pigs
- 15 April 2022
- Published by Elsevier in Journal of Genetics and Genomics
- Vol. 49 (11) , 1016-1028
Single-cell RNA-seq analysis of testicular somatic cell development in pigs
- Open Access
- 1 November 2021
- Published by Frontiers Media SA in Frontiers in Cell and Developmental Biology
- Vol. 9
The RNA Methyltransferase METTL3 Promotes Endothelial Progenitor Cell Angiogenesis in Mandibular Distraction Osteogenesis via the PI3K/AKT Pathway
Distraction osteogenesis (DO) is used to treat large bone defects in the field of oral and maxillofacial surgery. Successful DO-mediated bone regeneration is dependent upon angiogenesis, and endothelial progenitor cells (EPCs) are key mediators of angiogenic processes. The N6-methyladenosine (m6A) methyltransferase has been identified as an important regulator of diverse biological processes, but its role in EPC-mediated angiogenesis during DO remains to be clarified. In the present study, we found that the level of m6A modification was significantly elevated during the process of DO and that it was also increased in the context of EPC angiogenesis under hypoxic conditions, which was characterized by increased METTL3 levels. After knocking down METTL3 in EPCs, m6A RNA methylation, proliferation, tube formation, migration, and chicken embryo chorioallantoic membrane (CAM) angiogenic activity were inhibited, whereas the opposite was observed upon the overexpression of METTL3. Mechanistically, METTL3 silencing reduced the levels of VEGF and PI3Kp110 as well as the phosphorylation of AKT, whereas METTL3 overexpression reduced these levels. SC79-mediated AKT phosphorylation was also able to restore the angiogenic capabilities of METTL3-deficient EPCs in vitro and ex vivo. In vivo, METTL3-overexpressing EPCs were additionally transplanted into the DO callus, significantly enhancing bone regeneration as evidenced by improved radiological and histological manifestations in a canine mandibular DO model after consolidation over a 4-week period. Overall, these results indicate that METTL3 accelerates bone regeneration during DO by enhancing EPC angiogenesis via the PI3K/AKT pathway.
- 1 November 2021
- Published by Frontiers Media SA in Frontiers in Cell and Developmental Biology
- Vol. 9
Open AccessThe RNA Methyltransferase METTL3 Promotes Endothelial Progenitor Cell Angiogenesis in Mandibular Distraction Osteogenesis via the PI3K/AKT Pathway
Distraction osteogenesis (DO) is used to treat large bone defects in the field of oral and maxillofacial surgery. Successful DO-mediated bone regeneration is dependent upon angiogenesis, and endothelial progenitor cells (EPCs) are key mediators of angiogenic processes. The N6-methyladenosine (m6A) methyltransferase has been identified as an important regulator of diverse biological processes, but its role in EPC-mediated angiogenesis during DO remains to be clarified. In the present study, we found that the level of m6A modification was significantly elevated during the process of DO and that it was also increased in the context of EPC angiogenesis under hypoxic conditions, which was characterized by increased METTL3 levels. After knocking down METTL3 in EPCs, m6A RNA methylation, proliferation, tube formation, migration, and chicken embryo chorioallantoic membrane (CAM) angiogenic activity were inhibited, whereas the opposite was observed upon the overexpression of METTL3. Mechanistically, METTL3 silencing reduced the levels of VEGF and PI3Kp110 as well as the phosphorylation of AKT, whereas METTL3 overexpression reduced these levels. SC79-mediated AKT phosphorylation was also able to restore the angiogenic capabilities of METTL3-deficient EPCs in vitro and ex vivo. In vivo, METTL3-overexpressing EPCs were additionally transplanted into the DO callus, significantly enhancing bone regeneration as evidenced by improved radiological and histological manifestations in a canine mandibular DO model after consolidation over a 4-week period. Overall, these results indicate that METTL3 accelerates bone regeneration during DO by enhancing EPC angiogenesis via the PI3K/AKT pathway.