Sheng Gao

Sheng Gao


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
22 May 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Lianlei LinLianlei Lin
Lianlei Lin
HZHanqing Zhao
Hanqing Zhao
SGSheng Gao
Sheng Gao
Junkai WangJunkai Wang
Junkai Wang
ZZZongwei Zhang
Zongwei Zhang
In realistic hyperspectral image (HSI) cross-scene classification tasks, it is ideal to obtain target domain samples during the training phase. Therefore, a model needs to be trained on one or more source domains (SD) and achieve robust domain generalization (DG) performance on an unknown target domain (TD). Popular DG strategies constrain the model’s predictive behavior in synthetic space through deep, nonlinear source expansion, and an HSI generation model is usually adopted to enrich the diversity of training samples. However, recent studies have shown that the activation functions of neurons in a network exhibit asymmetry for different categories, which results in the learning of task-irrelevant features while attempting to learn task-related features (called “feature contamination”). For example, even if some intrinsic features of HSIs (lighting conditions, atmospheric environment, etc.) are irrelevant to the label, the neural network still tends to learn them, resulting in features that make the classification related to these spurious components. To alleviate this problem, this study replaces the common nonlinear generative network with a specific linear projection transformation, to reduce the number of neurons activated nonlinearly during training and alleviate the learning of contaminated features. Specifically, this study proposes a dimensionally decoupled spatial spectral linear extrapolation (SSLE) strategy to achieve sample augmentation. Inspired by the weakening effect of water vapor absorption and Rayleigh scattering on band reflectivity, we simulate a common spectral drift based on Markov random fields to achieve linear spectral augmentation. Further considering the common co-occurrence phenomenon of patch images in space, we design spatial weights combined with label determinism of the center pixel to construct linear spatial enhancement. Finally, to ensure the cognitive unity of the high-level features of the discriminator in the sample space, we use inter-class contrastive learning to align the back-end feature representation. Extensive experiments were conducted on four datasets, an ablation study showed the effectiveness of the proposed modules, and a comparative analysis with advanced DG algorithms showed the superiority of our model in the face of various spectral and category shifts. In particular, on the Houston18/Shanghai datasets, its overall accuracy was 0.51%/0.83% higher than the best results of the other methods, and its Kappa coefficient was 0.78%/2.07% higher, respectively.

17 April 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Junkai WangJunkai Wang
Junkai Wang
Lianlei LinLianlei Lin
Lianlei Lin
YZYu Zhang
Yu Zhang
ZZZongwei Zhang
Zongwei Zhang
SGSheng Gao
Sheng Gao
HZHanqing Zhao
Hanqing Zhao
Time downscaling is one of the most challenging topics in remote sensing and meteorological data processing. Traditional methods often face the problems of high computing cost and poor generalization ability. The framework interpolation method based on deep learning provides a new idea for the time downscaling of meteorological data. A deep neural network for the time downscaling of multivariate meteorological data is designed in this paper. It estimates the kernel weight and offset vector of each target pixel independently among different meteorological variables and generates output frames guided by the feature space. Compared with other methods, this model can deal with a large range of complex meteorological movements. The 2 h interval downscaling experiments for 2 m temperature, surface pressure, and 1000 hPa specific humidity show that the MAE of the proposed method is reduced by about 14%, 25%, and 18%, respectively, compared with advanced methods such as AdaCof and Zooming Slow-Mo. Performance fluctuates very little over time, with an average performance fluctuation of only about 1% across all metrics. Even in the downscaling experiment with a 6 h interval, the proposed model still maintains a leading performance advantage, which indicates that the proposed model has not only good performance and robustness but also excellent scalability and transferability in the downscaling task in the multivariate meteorological field.

1 August 2025 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
YTYuzhe Tan
Yuzhe Tan
GMGong Meng
Gong Meng
XGXiao Geng
Xiao Geng
SGSheng Gao
Sheng Gao
This study addresses the technical limitations of the Modelica-based simulation mode in the dynamic interaction characteristics of simulation systems within measurement and control systems. It proposes the C-Modelica co-simulation architecture, which establishes a parameter read/write channel for the Modelica static model through the shared memory middleware. By constructing a dynamic compilation interface for control logic using C code blocks, the architecture allows dynamic modification of digital model parameters during the simulation process, enabling external injection of user control behaviors. The proposed C-Modelica co-simulation architecture’s dynamic behavior control capabilities during the simulation process are verified by using commonly used switch driver functional modules in measurement and control systems. This provides theoretical and practical support for digital model construction and behavior validation in measurement and control systems.

15 June 2026 in Energies
Verified
Journal Article
Open access
PDF file
HYHangyi Yu
Hangyi Yu
SGSheng Gao
Sheng Gao
HZHanqing Zhao
Hanqing Zhao
YZYu Zhang
Yu Zhang
Lianlei LinLianlei Lin
Lianlei Lin
Junkai WangJunkai Wang
Junkai Wang
Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting.