Zijiang Song

Zijiang Song

Auto-generated profile, based on publicly available information

Zijiang Song

Key Laboratory of Geographic Information Science, Ministry of Education, School of Geographic Sciences, East China Normal University, Shanghai 200241, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 October 2022 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZSZijiang Song
Zijiang Song
BZBaojiang Zhong
Baojiang Zhong
JJJiahuan Ji
Jiahuan Ji
KMKai-Kuang Ma
Kai-Kuang Ma
The non-local attention mechanism has often been exploited in deep learning to capture long-range dependencies (LRDs) from the same image for enhancing the performance of various image processing methods. However, the initially proposed non-local attention process inevitably yields extremely-high computation complexity, since all the feature points are involved in computing the LRDs. To address this concern, a recently proposed criss-cross network (CCNet), which has a recurrent criss-cross attention (RCCA) module, is used to compute the LRDs by involving only a small set of feature points for significantly reducing computation. Motivated by the RCCA, a novel direction-decoupled non-local attention (DNA) module is proposed in this paper that is able to further reduce the computation complexity of RCCA by half approximately. To verify the performance of our new non-local attention module, a DNA network is developed for conducting single image super-resolution (SISR). Extensive experimental results have clearly demonstrated the superiority of using our DNA network for SISR when compared with that of state-of-the-art methods.

7 September 2024 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
YLYuying Li
Yuying Li
Lina YUANLina YUAN
Lina YUAN
ZSZijiang Song
Zijiang Song
SYShanshan Yu
Shanshan Yu
XZXiaowen Zhang
Xiaowen Zhang
MLMin Liu
Min Liu


11 April 2025 in Earth System Science Data
Verified
Journal Article
Open access
PDF file
ZSZijiang Song
Zijiang Song
ZCZhixiang Cheng
Zhixiang Cheng
YLYuying Li
Yuying Li
SYShanshan Yu
Shanshan Yu
XZXiaowen Zhang
Xiaowen Zhang
MLMin Liu
Min Liu
The long-term and reliable meteorological reanalysis dataset with high spatial–temporal resolution is crucial for various hydrological and meteorological applications, especially in regions or periods with scarce in situ observations and with limited open-access data. Based on the fifth-generation reanalysis dataset (ERA5, produced by the European Centre for Medium-Range Weather Forecasts, 0.25°×0.25°, since 1940) and CLDAS (China Meteorological Administration Land Data Assimilation System, 0.0625°×0.0625°, since 2008), we propose a novel downscaling method Geopotential-guided Attention Network (GeoAN), leveraging the high spatial resolution of CLDAS and the extended historical coverage of ERA5, and produce the daily multi-variable (2 m temperature, surface pressure, and 10 m wind speed) meteorological dataset MDG625. MDG625 (0.0625° Meteorological Dataset derived by GeoAN) covers most of Asia from 0.125° S to 64.875° N and 60.125 to 160.125° E, and contains data starting in 1940. Compared with other downscaling methods, GeoAN shows better performance with R2 (2 m temperature, surface pressure, and 10 m wind speed reach 0.990, 0.998, and 0.781, respectively). MDG625 demonstrates superior continuity and consistency from both spatial and temporal perspectives. We anticipate that the GeoAN method and this dataset, MDG625, will aid in climate studies of Asia and will contribute to improving the accuracy of reanalysis products from the 1940s. The MDG625 dataset (Song et al., 2024) is presented at https://doi.org/10.57760/sciencedb.17408, and the code can be found at https://github.com/songzijiang/GeoAN (last access: 8 April 2025).

23 April 2026 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
ZSZijiang Song
Zijiang Song
TLTing Liu
Ting Liu
Lina YUANLina YUAN
Lina YUAN
YLYuying Li
Yuying Li
AXAo Xu
Ao Xu
MLMin Liu
Min Liu

24 June 2024 in EGUsphere
Verified
Preprint
Open access
PDF file
ZSZijiang Song
Zijiang Song
ZCZhixiang Cheng
Zhixiang Cheng
YLYuying Li
Yuying Li
SYShanshan Yu
Shanshan Yu
XZXiaowen Zhang
Xiaowen Zhang
MLMin Liu
Min Liu
The long-term and reliable meteorological reanalysis dataset with high spatial-temporal resolution is crucial for various hydrological and meteorological applications, especially in regions or periods with scarce in situ observations and with limited open-access data. Based on the ERA5 (produced by the European Centre for Medium-Range Weather Forecasts, 0.25°×0.25°, since 1940) and CLDAS (China Meteorological Administration Land Data Assimilation System, 0.0625°×0.0625°, since 2008), we proposed a novel downscaling method Geopotential-guide Attention Network (GeoAN) leveraging the high spatial resolution of CLDAS and the extended historical coverage of ERA5 and produced the daily multi-variable (2 m temperature, surface pressure, and 10 m wind speed) meteorological dataset MDG625 (Song et al., 2024). MDG625 (0.0625° Meteorological Dataset derived by GeoAN) covers most of Asia from 0.125° S to 64.875° N and 60.125° E to 160.125° E since 1940. Compared with other downscaling methods, GeoAN shows better performance with the R2 (2 m temperature, surface pressure, and 10 m wind speed reached 0.990, 0.998, and 0.781, respectively). MDG625 demonstrates superior continuity and consistency from both spatial and temporal perspectives. We anticipate that this GeoAN method and this dataset MDG625 will aid in climate studies of Asia and will contribute to improving the accuracy of reanalysis products from the 1940s. The dataset (Song et al., 2024) is presented in https://doi.org/10.57760/sciencedb.17408 and the code can be found in https://github.com/songzijiang/GeoAN.