Peng Li

Peng Li

Auto-generated profile, based on publicly available information

Peng Li

College of Harbour and Coastal Engineering, Jimei University, Xiamen 361021, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
WXWei Xu
Wei Xu
SCShenliang Chen
Shenliang Chen
HJHongyu Ji
Hongyu Ji
THTaihuan Hu
Taihuan Hu
XZXiaojing Zhong
Xiaojing Zhong
PLPeng Li
Peng Li
Beach erosion and shoreline dynamics are strongly affected by alterations in nearshore wave intensity and energy, especially in the context of global climate change. However, existing works do not thoroughly study the evolution of the sandy coasts of eastern Hainan Island, China, nor their responses to wave climate change driven by climate variability. This study focuses on the open sandy coast and assesses shoreline evolutionary dynamics in response to wave climate variability over a 30-year period from 1994 to 2023, using an open-source software toolkit that semi-automatically identify the shorelines (CoastSat v2.4) and reanalysis wave datasets (ERA5). The shorelines of the study area were extracted from CoastSat, and then tidal correction and outlier correction were performed for clearer shorelines. Combining the shoreline changes and wave conditions derived from ERA5, the dynamics of the shorelines and their response to wave climate change were further studied. The findings reveal that the average long-term shoreline change rate along the eastern coast of Hainan Island is 0.03 m/year, with 44.8% of transects experiencing erosion and 55.2% showing long-term accretion. And distinct evolutionary patterns emerge across different sections. Interannual variability is marked by alternating erosion and siltation cycles, while most sections of the coast experiences clear seasonal fluctuations, with accretion typically occurring during summer and erosion occurring in winter. El Niño–Southern Oscillation (ENSO) cycles drive changes in parameters including significant wave height, mean wave period, wave energy flux, and mean wave direction, leading to long-term changes in wave climate. The multi-scale behavior of the sandy shoreline responds distinctly to the ongoing changes in wave climate triggered by ENSO viability, with El Niño events typically resulting in accretion and La Niña periods causing erosion. Notably, mean wave direction is the metric most closely linked to changes in the shoreline among all the others. In conclusion, the interplay of escalating anthropogenic activities, natural processes, and climate change contributes to the long-term evolution of sandy shorelines. We believe this study can offer a scientific reference for erosion prevention and management strategies of sandy beaches, based on the analysis presented above.

26 May 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
YPYiheng Pan
Yiheng Pan
YZYongqi Zhang
Yongqi Zhang
FZFanqin Zeng
Fanqin Zeng
PLPeng Li
Peng Li
PXpeng xia
peng xia
QLQiqi Luo
Qiqi Luo
This study proposes an enhanced physics-informed neural network (PINN) framework for predicting seepage fields around deeply buried tunnels with limited field measurements. Hard-constrained boundary enforcement via distance-function trial functions is introduced to exactly satisfy Dirichlet conditions on both the ground surface and tunnel perimeter, and Bayesian optimization automates loss weight tuning to replace costly manual calibration. A systematic evaluation of 15 sensor placement schemes demonstrates that the hydraulic head variance across monitoring points, governed by radial coverage distance, is the primary determinant of prediction accuracy—not the number of sensors or angular density. Remarkably, a strategically designed 12-point configuration outperforms 100 randomly distributed points under the idealized conditions studied, confirming that placement quality can dominate over quantity when physics-informed optimization is applied. Transfer learning experiments across 132 geometric configurations reveal a previously unreported geometric transition zone at D/R ≈ 13–15, where prediction errors exhibit a distinct non-monotonic peak. Finite element benchmarking confirms that this error peak stems from the learning characteristics of PINNs under competing boundary influences rather than from the physical complexity of the problem itself. High-density sampling effectively suppresses this peak error by 32% compared with sparse sampling. These findings establish quantitative sensor deployment guidelines for tunnel seepage monitoring and identify fundamental performance boundaries of physics-informed machine learning under geometry–physics coupling.