Feiyi Liu

Dr. Feiyi Liu

orcid
May this jorney lead us starward!

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
9 October 2023 in Physical Review D
Verified
Journal Article
Open access
PDF file
FMFei Ma
Fei Ma
Feiyi LiuFeiyi Liu
Feiyi Liu
WLWei Li
Wei Li
Recently, methods of graph neural networks (GNNs) have been applied to solving the problems in high-energy physics (HEP) and have shown its great potential for quark-gluon tagging with graph representation of jet events. In this paper, we introduce an approach of GNNs combined with a Haar pooling operation to analyze the events, called Haar pooling message passing neural network (HMPNet). In HMPNet, Haar pooling not only extracts the features of graph, but embeds additional information obtained by clustering of k means of different particle features. We construct Haar pooling from five different features: absolute energy logE, transverse momentum logpT, relative coordinates (Δη,Δϕ), the mixed ones (logE,logpT), and (logE,logpT,Δη,Δϕ). The results show that an appropriate selection of information for Haar pooling enhances the accuracy of quark-gluon tagging, as adding extra information of logPT to the HMPNet outperforms all the others, whereas adding relative coordinates information (Δη,Δϕ) is not very effective. This implies that, by adding effective particle features from Haar pooling, one can achieve much better results than that which a solely pure message passing neutral network can do, which demonstrates significant improvement of feature extraction via the pooling process. Finally, we compare the HMPNet study, ordering by pT, with other studies and prove that the HMPNet is also a good choice of GNN algorithms for jet tagging.

30 June 2022 in Physical Review E
Verified
Journal Article
Closed access
PDF file
JSJianmin Shen
Jianmin Shen
Feiyi LiuFeiyi Liu
Feiyi Liu
SCShiyang Chen
Shiyang Chen
DXDian Xu
Dian Xu
XCXiangna Chen
Xiangna Chen
CYC. B. Yang
C. B. Yang
The latest advances of statistical physics have shown remarkable performance of machine learning in identifying phase transitions. In this paper, we apply domain adversarial neural network (DANN) based on transfer learning to studying nonequilibrium and equilibrium phase transition models, which are percolation model and directed percolation (DP) model, respectively. With the DANN, only a small fraction of input configurations (two-dimensional images) needs to be labeled, which is automatically chosen, to capture the critical point. To learn the DP model, the method is refined by an iterative procedure in determining the critical point, which is a prerequisite for the data collapse in calculating the critical exponent ν⊥. We then apply the DANN to a two-dimensional site percolation with configurations filtered to include only the largest cluster which may contain the information related to the order parameter. The DANN learning of both models yields reliable results which are comparable to the ones from Monte Carlo simulations. Our study also shows that the DANN can achieve quite high accuracy at much lower cost, compared to the supervised learning.

17 November 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJianmin Shen
Jianmin Shen
WLWei Li
Wei Li
SDShengfeng Deng
Shengfeng Deng
DXDian Xu
Dian Xu
SCShiyang Chen
Shiyang Chen
Feiyi LiuFeiyi Liu
Feiyi Liu
The pair-contact process with diffusion (PCPD), a generalized model of the ordinary pair-contact process (PCP) without diffusion, exhibits a continuous absorbing phase transition. Unlike the PCP, whose nature of phase transition is clearly classified into the directed percolation (DP) universality class, the model of PCPD has been controversially discussed since its infancy. To our best knowledge, there is so far no consensus on whether the phase transition of the PCPD falls into the unknown university classes or else conveys a new kind of non-equilibrium phase transition. In this paper, both unsupervised and supervised learning are employed to study the PCPD with scrutiny. Firstly, two unsupervised learning methods, principal component analysis (PCA) and autoencoder, are taken. Our results show that both methods can cluster the original configurations of the model and provide reasonable estimates of thresholds. Therefore, no matter whether the non-equilibrium lattice model is a random process of unitary (for instance the DP) or binary (for instance the PCP), or whether it contains the diffusion motion of particles, unsupervised learning can capture the essential, hidden information. Beyond that, supervised learning is also applied to learning the PCPD at different diffusion rates. We proposed a more accurate numerical method to determine the spatial correlation exponent $$\nu _{\perp }$$ ν ⊥ , which, to a large degree, avoids the uncertainty of data collapses through naked eyes.

9 March 2023 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
XCXiangna Chen
Xiangna Chen
Feiyi LiuFeiyi Liu
Feiyi Liu
SCShiyang Chen
Shiyang Chen
JSJianmin Shen
Jianmin Shen
WDWeibing Deng
Weibing Deng
CYChunbin Yang
Chunbin Yang

9 May 2025 in Energies
Verified
Journal Article
Open access
PDF file
XZXing-Fa Zi
Xing-Fa Zi
Feiyi LiuFeiyi Liu
Feiyi Liu
MLMing-Yang Liu
Ming-Yang Liu
YWYang Wang
Yang Wang
Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–decoder model, to forecast PV power generation. TiDE compresses historical time series and covariates into latent representations via residual connections and reconstructs future values through a temporal decoder, capturing both long- and short-term dependencies. We trained the model using data from 2020 to 2022 from Australia’s Desert Knowledge Australia Solar Centre (DKASC), with 2023 data used for testing. Forecast accuracy was evaluated using the R2 coefficient of determination, mean absolute error (MAE), and root mean square error (RMSE). In the 5 min ahead forecasting test, TiDE demonstrated high short-term accuracy with an R2 of 0.952, MAE of 0.150, and RMSE of 0.349, though performance declines for longer horizons, such as the 1 h ahead forecast, compared to other algorithms. For one-day-ahead forecasts, it achieved an R2 of 0.712, an MAE of 0.507, and an RMSE of 0.856, effectively capturing medium-term weather trends but showing limited responsiveness to sudden weather changes. Further analysis indicated improved performance in cloudy and rainy weather, and seasonal analysis reveals higher accuracy in spring and autumn, with reduced accuracy in summer and winter due to extreme conditions. Additionally, we explore the TiDE model’s sensitivity to input environmental variables, algorithmic versatility, and the implications of forecasting errors on PV grid integration. These findings highlight TiDE’s superior forecasting accuracy and robust adaptability across weather conditions, while also revealing its limitations under abrupt changes.

18 January 2024 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
XCXiangna Chen
Xiangna Chen
Feiyi LiuFeiyi Liu
Feiyi Liu
WDWeibing Deng
Weibing Deng
SCShiyang Chen
Shiyang Chen
JSJianmin Shen
Jianmin Shen
CYChunbin Yang
Chunbin Yang