Chengwei Yu

Research Subjects

Research Interests

Chengwei Yu has a total of 35 co-authors. Here are the top co-authors by number of shared publications:

Huiying Wang
China Fire and Rescue Institue, 4 Nanyan Road, Changping District, Beijing 102202, China
4 shared publications
Yue Zeng
Beihang University, Haidian District, Beijing 100191, China
2 shared publications
A. D. Liu
Department of Plasma Physics and Fusion Engineering, University of Science and Technology of China, Hefei 230026, People’s Republic of China
1 shared publication
Cong Chen
Hainan Tropical Ocean University
1 shared publication
Defeng Kong
Institute of Energy, Hefei Comprehensive National Science Center (Anhui Energy Laboratory), Hefei 230031, China
1 shared publication
Ge Zhuang
University of Science and Technology of China
1 shared publication

Latest Publications

Sort by

Open Access
Website
Google Scholar
- 7 July 2026
- Published by MDPI AG in Symmetry
Lipschitz Regularity for a Non-Homogeneous Highly Degenerate q-Laplace Equation in the Heisenberg Group
by Huiying Wang, Chengwei Yu, Pei Li, Kunpeng Cui
In the Heisenberg group $H^{n}$ and for exponents $2 \leq q \leq 4$ , the local Lipschitz ( $C^{0, 1}$ ) regularity is demonstrated for weak solutions to a non-homogeneous highly degenerate q-Laplace equation of the form $- \sum_{i = 1}^{2 n} X_{i} (λ_{i} (X u) X_{i} u) = g (x)$ , where $λ_{i} (z) = {(z_{i}^{2} + z_{i + n}^{2})}^{\frac{q - 2}{2}}$ for $i = 1, \dots, n$ and $λ_{i} (z) = {(z_{i}^{2} + z_{i - n}^{2})}^{\frac{q - 2}{2}}$ for $i = n + 1, \dots, 2 n$ . Our approach draws heavily on the work of X. Zhong. However, owing to technical limitations, the regularity of weak solutions for $1 < q < 2$ and $4 < q < \infty$ remains unclear.
Website
Google Scholar
- 7 July 2026
- Published by MDPI AG in Symmetry
Open Access
Lipschitz Regularity for a Non-Homogeneous Highly Degenerate q-Laplace Equation in the Heisenberg Group
by Huiying Wang, Chengwei Yu, Pei Li, Kunpeng Cui
In the Heisenberg group $H^{n}$ and for exponents $2 \leq q \leq 4$ , the local Lipschitz ( $C^{0, 1}$ ) regularity is demonstrated for weak solutions to a non-homogeneous highly degenerate q-Laplace equation of the form $- \sum_{i = 1}^{2 n} X_{i} (λ_{i} (X u) X_{i} u) = g (x)$ , where $λ_{i} (z) = {(z_{i}^{2} + z_{i + n}^{2})}^{\frac{q - 2}{2}}$ for $i = 1, \dots, n$ and $λ_{i} (z) = {(z_{i}^{2} + z_{i - n}^{2})}^{\frac{q - 2}{2}}$ for $i = n + 1, \dots, 2 n$ . Our approach draws heavily on the work of X. Zhong. However, owing to technical limitations, the regularity of weak solutions for $1 < q < 2$ and $4 < q < \infty$ remains unclear.
Open Access
Website
Google Scholar
- 6 January 2026
- Published by MDPI AG in AppliedMath
Spatial Prediction of Forest Fire Risk in Guangdong Province Using Multi-Source Geospatial Data and Sparrow Search Algorithm-Optimized XGBoost
by Huiying Wang, Chengwei Yu, Jiahuan Wang
Forest fires pose escalating threats to ecological security and public safety in Guangdong Province. This study presents a novel machine learning framework for fire occurrence prediction by synergistically integrating multi-source geospatial data. Utilizing Moderate-resolution Imaging Spectroradiometer (MODIS) active fire detections from 2014 to 2023, we quantified historical fire patterns and incorporated four categories of predisposing factors: meteorological variables, topographic attributes, vegetation characteristics, and anthropogenic activities. Spatiotemporal clustering dynamics were characterized via kernel density estimation and spatial autocorrelation analysis. An XGBoost classifier, hyperparameter-optimized through the Sparrow Search Algorithm (SSA), achieved a predictive accuracy of 90.4%, with performance evaluated through precision, recall, and $F_{1}$ -score. Risk zoning maps generated from predicted probabilities were validated against independent fire records from 2019 to 2024. Results reveal pronounced spatial heterogeneity, with high-risk zones concentrated in northern and western mountainous areas, constituting 29% of the provincial territory. Critical driving factors include slope gradient, proximity to roads and rivers, temperature, population density, and elevation. This robust predictive framework furnishes a scientific foundation for spatially-explicit fire prevention strategies and optimized resource allocation in key high-risk jurisdictions, notably Qingyuan, Shaoguan, Zhanjiang, and Zhaoqing.
Website
Google Scholar
- 6 January 2026
- Published by MDPI AG in AppliedMath
Open Access
Spatial Prediction of Forest Fire Risk in Guangdong Province Using Multi-Source Geospatial Data and Sparrow Search Algorithm-Optimized XGBoost
by Huiying Wang, Chengwei Yu, Jiahuan Wang
Forest fires pose escalating threats to ecological security and public safety in Guangdong Province. This study presents a novel machine learning framework for fire occurrence prediction by synergistically integrating multi-source geospatial data. Utilizing Moderate-resolution Imaging Spectroradiometer (MODIS) active fire detections from 2014 to 2023, we quantified historical fire patterns and incorporated four categories of predisposing factors: meteorological variables, topographic attributes, vegetation characteristics, and anthropogenic activities. Spatiotemporal clustering dynamics were characterized via kernel density estimation and spatial autocorrelation analysis. An XGBoost classifier, hyperparameter-optimized through the Sparrow Search Algorithm (SSA), achieved a predictive accuracy of 90.4%, with performance evaluated through precision, recall, and $F_{1}$ -score. Risk zoning maps generated from predicted probabilities were validated against independent fire records from 2019 to 2024. Results reveal pronounced spatial heterogeneity, with high-risk zones concentrated in northern and western mountainous areas, constituting 29% of the provincial territory. Critical driving factors include slope gradient, proximity to roads and rivers, temperature, population density, and elevation. This robust predictive framework furnishes a scientific foundation for spatially-explicit fire prevention strategies and optimized resource allocation in key high-risk jurisdictions, notably Qingyuan, Shaoguan, Zhanjiang, and Zhaoqing.
Open Access
Website
Google Scholar
Cited by 8
- 6 August 2025
- Published by Springer Nature in The Visual Computer
Advancing landslide recognition through multi-dimensional feature fusion and transformer architectures
by Cong Chen, Chengwei Yu, Shanshan Cai
Landslides are a type of sudden and highly destructive geological hazard. Traditional detection methods often suffer from delayed response and low efficiency. In recent years, deep learning-based object detection techniques have attracted increasing attention in disaster recognition tasks, particularly transformer-based detection models, which exhibit significant advantages in global feature modeling. However, landslide targets in remote sensing imagery often present challenges such as large-scale variation, blurred boundaries, and texture interference. To address these issues, this study proposes an improved detection algorithm based on the RT-DETR-r18 framework by integrating multiple specialized modules. First, the DDC3 module is designed to enhance the recognition of fine boundaries and local textures, thereby improving the feature extraction capacity of the backbone network. Second, an Efficient Additive Attention (EAA) mechanism is introduced to suppress redundant information and strengthen the model's focus on critical regions, improving detection precision. Finally, the CGAFusion module is employed, which utilizes a triple-attention strategy to collaboratively regulate feature weights. This module enhances the model’s ability to filter salient features while preserving global contextual information, leading to more accurate landslide edge detection. A dual-class dataset comprising landslides and storms is constructed from multi-source imagery for evaluation. The experimental results show that the proposed method outperforms existing models in several dimensions including mAP@0.5 and F1 score, demonstrating strong detection accuracy. Code is available at https://github.com/sanyauChenCoder/Landslide_02.git.
Website
Google Scholar
- 6 August 2025
- Published by Springer Nature in The Visual Computer
Open Access
Advancing landslide recognition through multi-dimensional feature fusion and transformer architectures
by Cong Chen, Chengwei Yu, Shanshan Cai
Landslides are a type of sudden and highly destructive geological hazard. Traditional detection methods often suffer from delayed response and low efficiency. In recent years, deep learning-based object detection techniques have attracted increasing attention in disaster recognition tasks, particularly transformer-based detection models, which exhibit significant advantages in global feature modeling. However, landslide targets in remote sensing imagery often present challenges such as large-scale variation, blurred boundaries, and texture interference. To address these issues, this study proposes an improved detection algorithm based on the RT-DETR-r18 framework by integrating multiple specialized modules. First, the DDC3 module is designed to enhance the recognition of fine boundaries and local textures, thereby improving the feature extraction capacity of the backbone network. Second, an Efficient Additive Attention (EAA) mechanism is introduced to suppress redundant information and strengthen the model's focus on critical regions, improving detection precision. Finally, the CGAFusion module is employed, which utilizes a triple-attention strategy to collaboratively regulate feature weights. This module enhances the model’s ability to filter salient features while preserving global contextual information, leading to more accurate landslide edge detection. A dual-class dataset comprising landslides and storms is constructed from multi-source imagery for evaluation. The experimental results show that the proposed method outperforms existing models in several dimensions including mAP@0.5 and F1 score, demonstrating strong detection accuracy. Code is available at https://github.com/sanyauChenCoder/Landslide_02.git.
Cited by 8
Open Access
Website
Google Scholar
- 21 May 2025
- Published by MDPI AG in Symmetry
Lipschitz and Second-Order Regularities for Non-Homogeneous Degenerate Nonlinear Parabolic Equations in the Heisenberg Group
by Huiying Wang, Chengwei Yu, Zhiqiang Zhang, Yue Zeng
In the Heisenberg group $H^{n}$ , we establish the local regularity theory for weak solutions to non-homogeneous degenerate nonlinear parabolic equations of the form $\partial_{t} u - \sum_{i = 1}^{2 n} X_{i} A_{i} (X u) = K (x, t, u, X u)$ , where the nonlinear structure is modeled on non-homogeneous parabolic p-Laplacian-type operators. Specifically, we prove two main local regularities: (i) For $2 \leq p \leq 4$ , we establish the local Lipschitz regularity ( $u \in C_{loc}^{0, 1}$ ), with the horizontal gradient satisfying $X u \in L_{loc}^{\infty}$ ; (ii) For $2 \leq p < 3$ , we establish the local second-order horizontal Sobolev regularity ( $u \in H W_{loc}^{2, 2}$ ), with the second-order horizontal derivative satisfying $X X u \in L_{loc}^{2}$ . These results solve an open problem proposed by Capogna et al.
Website
Google Scholar
- 21 May 2025
- Published by MDPI AG in Symmetry
Open Access
Lipschitz and Second-Order Regularities for Non-Homogeneous Degenerate Nonlinear Parabolic Equations in the Heisenberg Group
by Huiying Wang, Chengwei Yu, Zhiqiang Zhang, Yue Zeng
In the Heisenberg group $H^{n}$ , we establish the local regularity theory for weak solutions to non-homogeneous degenerate nonlinear parabolic equations of the form $\partial_{t} u - \sum_{i = 1}^{2 n} X_{i} A_{i} (X u) = K (x, t, u, X u)$ , where the nonlinear structure is modeled on non-homogeneous parabolic p-Laplacian-type operators. Specifically, we prove two main local regularities: (i) For $2 \leq p \leq 4$ , we establish the local Lipschitz regularity ( $u \in C_{loc}^{0, 1}$ ), with the horizontal gradient satisfying $X u \in L_{loc}^{\infty}$ ; (ii) For $2 \leq p < 3$ , we establish the local second-order horizontal Sobolev regularity ( $u \in H W_{loc}^{2, 2}$ ), with the second-order horizontal derivative satisfying $X X u \in L_{loc}^{2}$ . These results solve an open problem proposed by Capogna et al.
Website
Google Scholar
- 10 April 2025
- Published by Elsevier in Bulletin des Sciences Mathématiques
Local second order horizontal Sobolev regularity for p-harmonic functions with Hörmander vector fields of step two
by Chengwei Yu, Yu Liu
Website
Google Scholar
- 10 April 2025
- Published by Elsevier in Bulletin des Sciences Mathématiques
Local second order horizontal Sobolev regularity for p-harmonic functions with Hörmander vector fields of step two
by Chengwei Yu, Yu Liu
Open Access
Website
Google Scholar
Cited by 1
- 8 November 2024
- Published by MDPI AG in Mathematics
Second-Order Regularity for Degenerate Parabolic Quasi-Linear Equations in the Heisenberg Group
by Chengwei Yu, Huiying Wang, Kunpeng Cui, Zijing Zhao
In the Heisenberg group $H^{n}$ , we obtain the local second-order $H W_{loc}^{2, 2}$ -regularity for the weak solution u to a class of degenerate parabolic quasi-linear equations $\partial_{t} u = \sum_{i = 1}^{2 n} X_{i} A_{i} (X u)$ modeled on the parabolic p-Laplacian equation. Specifically, when $2 \leq p \leq 4$ , we demonstrate the integrability of ${(\partial_{t} u)}^{2}$ , namely, $\partial_{t} u \in L_{loc}^{2}$ ; when $2 \leq p < 3$ , we demonstrate the $H W_{loc}^{2, 2}$ -regularity of u, namely, $X X u \in L_{loc}^{2}$ . For the $H W_{loc}^{2, 2}$ -regularity, when $p \geq 2$ , the range of p is optimal compared to the Euclidean case.
Website
Google Scholar
- 8 November 2024
- Published by MDPI AG in Mathematics
Open Access
Second-Order Regularity for Degenerate Parabolic Quasi-Linear Equations in the Heisenberg Group
by Chengwei Yu, Huiying Wang, Kunpeng Cui, Zijing Zhao
In the Heisenberg group $H^{n}$ , we obtain the local second-order $H W_{loc}^{2, 2}$ -regularity for the weak solution u to a class of degenerate parabolic quasi-linear equations $\partial_{t} u = \sum_{i = 1}^{2 n} X_{i} A_{i} (X u)$ modeled on the parabolic p-Laplacian equation. Specifically, when $2 \leq p \leq 4$ , we demonstrate the integrability of ${(\partial_{t} u)}^{2}$ , namely, $\partial_{t} u \in L_{loc}^{2}$ ; when $2 \leq p < 3$ , we demonstrate the $H W_{loc}^{2, 2}$ -regularity of u, namely, $X X u \in L_{loc}^{2}$ . For the $H W_{loc}^{2, 2}$ -regularity, when $p \geq 2$ , the range of p is optimal compared to the Euclidean case.
Cited by 1
Open Access
Website
Google Scholar
Cited by 1
- 24 April 2024
- Published by MDPI AG in Mathematics
Local C^0,1-Regularity for the Parabolic p-Laplacian Equation on the Group SU(3)
by Yongming He, Chengwei Yu, Hongqing Wang
In this article, when $2 \leq p \leq 4$ , we establish the $C_{loc}^{0, 1}$ -regularity of weak solutions to the degenerate parabolic p-Laplacian equation $\partial_{t} u = - \sum_{i = 1}^{6} X_{i}^{*} (| \nabla_{H} u |^{p - 2} X_{i} u)$ on the group SU(3) granted with horizontal vector fields $X_{1}, \dots, X_{6}$ . Compared to the Heisenberg group, $H^{n}$ , we obtained the optimal range of p; that is, $2 \leq p \leq 4$ .
Website
Google Scholar
- 24 April 2024
- Published by MDPI AG in Mathematics
Open Access
Local C^0,1-Regularity for the Parabolic p-Laplacian Equation on the Group SU(3)
by Yongming He, Chengwei Yu, Hongqing Wang
In this article, when $2 \leq p \leq 4$ , we establish the $C_{loc}^{0, 1}$ -regularity of weak solutions to the degenerate parabolic p-Laplacian equation $\partial_{t} u = - \sum_{i = 1}^{6} X_{i}^{*} (| \nabla_{H} u |^{p - 2} X_{i} u)$ on the group SU(3) granted with horizontal vector fields $X_{1}, \dots, X_{6}$ . Compared to the Heisenberg group, $H^{n}$ , we obtained the optimal range of p; that is, $2 \leq p \leq 4$ .
Cited by 1
Open Access
Website
Google Scholar
Cited by 2
- 17 February 2024
- Published by MDPI AG in Mathematics
Local Second Order Sobolev Regularity for p-Laplacian Equation in Semi-Simple Lie Group
by Chengwei Yu, Yue Zeng
In this paper, we establish a structural inequality of the ∞-subLaplacian $▵_{0, \infty}$ in a class of the semi-simple Lie group endowed with the horizontal vector fields $X_{1}, \dots, X_{2 n}$ . When $1 < p \leq 4$ with $n = 1$ and $1 < p < 3 + \frac{1}{n - 1}$ with $n \geq 2$ , we apply the structural inequality to obtain the local horizontal $W^{2, 2}$ -regularity of weak solutions to p-Laplacian equation in the semi-simple Lie group. Compared to Euclidean spaces $R^{2 n}$ with $n \geq 2$ , the range of this p obtained is already optimal.
Website
Google Scholar
- 17 February 2024
- Published by MDPI AG in Mathematics
Open Access
Local Second Order Sobolev Regularity for p-Laplacian Equation in Semi-Simple Lie Group
by Chengwei Yu, Yue Zeng
In this paper, we establish a structural inequality of the ∞-subLaplacian $▵_{0, \infty}$ in a class of the semi-simple Lie group endowed with the horizontal vector fields $X_{1}, \dots, X_{2 n}$ . When $1 < p \leq 4$ with $n = 1$ and $1 < p < 3 + \frac{1}{n - 1}$ with $n \geq 2$ , we apply the structural inequality to obtain the local horizontal $W^{2, 2}$ -regularity of weak solutions to p-Laplacian equation in the semi-simple Lie group. Compared to Euclidean spaces $R^{2 n}$ with $n \geq 2$ , the range of this p obtained is already optimal.
Cited by 2
Website
Google Scholar
Cited by 1
- 1 January 2023
- Published by Global Science Press in Journal of Mathematical Study
Regularity for $p$-Harmonic Functions in the Grušin Plane
by Chengwei Yu
$p$-Laplacian equation, regularities, Grusin plane. 35H20, 35B65 COPYRIGHT: © Global Science Press
Website
Google Scholar
- 1 January 2023
- Published by Global Science Press in Journal of Mathematical Study
Regularity for $p$-Harmonic Functions in the Grušin Plane
by Chengwei Yu
$p$-Laplacian equation, regularities, Grusin plane. 35H20, 35B65 COPYRIGHT: © Global Science Press
Cited by 1
Open Access
Website
Google Scholar
Cited by 3
- 5 November 2022
- Published by MDPI AG in Mathematics
Regularity for Quasi-Linear p-Laplacian Type Non-Homogeneous Equations in the Heisenberg Group
by Chengwei Yu
When $2 - 1 / Q < p \leq 2$ , we establish the $C_{loc}^{0, 1}$ and $C_{loc}^{1, α}$ -regularities of weak solutions to quasi-linear p-Laplacian type non-homogeneous equations in the Heisenberg group $H^{n}$ , where $Q = 2 n + 2$ is the homogeneous dimension of $H^{n}$ .
Website
Google Scholar
- 5 November 2022
- Published by MDPI AG in Mathematics
Open Access
Regularity for Quasi-Linear p-Laplacian Type Non-Homogeneous Equations in the Heisenberg Group
by Chengwei Yu
When $2 - 1 / Q < p \leq 2$ , we establish the $C_{loc}^{0, 1}$ and $C_{loc}^{1, α}$ -regularities of weak solutions to quasi-linear p-Laplacian type non-homogeneous equations in the Heisenberg group $H^{n}$ , where $Q = 2 n + 2$ is the homogeneous dimension of $H^{n}$ .
Cited by 3

Show all