Query：
学者姓名：赖晓鹤
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
The construction of an interval prediction model capable of explaining deformation uncertainties is crucial for the long-term safe operation of dams. High effective coverage and narrow interval coverage widths are two key benchmarks to ensure that the prediction interval (PI) can accurately quantify deformation uncertainties. The vast majority of existing models neglect to control the interval coverage width, and overly wide PIs can cause decision confusion when operators are developing safety plans for hydraulic structures. To address this problem, this paper proposes a novel interval prediction model combining bidirectional long-short-term memory network (Bi-LSTM) and split conformal quantile prediction (SCQP) for dam deformation prediction. The model uses Bi-LSTM as a benchmark regressor to extract and explain the nonlinear feature of dam deformation in the continuous time domain. SCQP is used to quantify the uncertainties in dam deformation prediction to ensure that the constructed PI can achieve high effective coverage while further improving the accuracy of the quantification of deformation uncertainties. The effectiveness of the proposed model is validated using deformation monitoring data collected from an arch dam in China. The results show that the average prediction interval effective coverage (PICP) of the proposed model is as high as 0.951 while the mean prediction interval width (MPIW) and coverage width-based criterion (CWC) are both only 5.815 mm. Compared with other models, the proposed method can construct higher-quality PIs, thus providing a better service for the safety assessment of dams.
Keyword ：
Bi-LSTM Bi-LSTM dam deformation prediction dam deformation prediction interval prediction interval prediction split conformal quantile prediction split conformal quantile prediction uncertainty quantification uncertainty quantification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Yan , Fu, Jiayuan , Lin, Weiwei et al. Dam Deformation Monitoring Model Based on Deep Learning and Split Conformal Quantile Prediction [J]. | APPLIED SCIENCES-BASEL , 2025 , 15 (4) . |
| MLA | Su, Yan et al. "Dam Deformation Monitoring Model Based on Deep Learning and Split Conformal Quantile Prediction" . | APPLIED SCIENCES-BASEL 15 . 4 (2025) . |
| APA | Su, Yan , Fu, Jiayuan , Lin, Weiwei , Lin, Chuan , Lai, Xiaohe , Xie, Xiudong . Dam Deformation Monitoring Model Based on Deep Learning and Split Conformal Quantile Prediction . | APPLIED SCIENCES-BASEL , 2025 , 15 (4) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The Yangtze River-Dongting Lake link has gotten a lot of attention as a because of the Three Gorges Project. However, the hydrological dynamic process and future direction of the river-lake interaction in the context of sediment reduction are yet unknown. Based on Dongting Lake Basin runoff and sediment data from 1961 to 2020, as well as field monitoring data of turbidity and flow velocity from Yichang to Chenglingji section of the Yangtze River, this paper examines the runoff and sediment variation law and hydrological dynamic process of Chenglingji, the only outlet connecting Dongting Lake to the Yangtze River, and reveals the development trend of the river-lake relationship. After absorbing high-concentration material from Dongting Lake, Chenglingji's turbidity and energy per unit water body alter dramatically. When the high-speed flow from the mainstream of the Yangtze River and the gentle flow of Dongting Lake pass through the "deep trough" of Chenglingji, the two streams of high and low flow velocity intersect and decelerate to dissipate energy, and the flow structure becomes more complicated. Dongting Lake has experienced three stages: deposition (1961-2007) -erosion (2008-2017) -deposition (2018-2020). The river-lake relationship will tend to a new dynamic equilibrium state in the future.
Keyword ：
Dam construction Dam construction Dongting lake Dongting lake Hydrological process Hydrological process River-lake relationship River-lake relationship Yangtze river Yangtze river
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lai, Xiaohe , Zou, Huangjie , Jiang, Jun et al. Hydrological dynamics of the Yangtze river-Dongting lake system after the construction of the three Gorges dam [J]. | SCIENTIFIC REPORTS , 2025 , 15 (1) . |
| MLA | Lai, Xiaohe et al. "Hydrological dynamics of the Yangtze river-Dongting lake system after the construction of the three Gorges dam" . | SCIENTIFIC REPORTS 15 . 1 (2025) . |
| APA | Lai, Xiaohe , Zou, Huangjie , Jiang, Jun , Jia, Jianping , Liu, Yan , Wei, Wen . Hydrological dynamics of the Yangtze river-Dongting lake system after the construction of the three Gorges dam . | SCIENTIFIC REPORTS , 2025 , 15 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
An accurate and reliable multi-step prediction model for dam displacement prediction can provide decision- makers with crucial forecast information, mitigating safety risks associated with abnormal displacements. However, conventional deep learning models overlook the variability exhibited by the lag effect of dam displacement in continuous time domains. The detrimental effect of this limitation on model performance is further amplified in the dam displacement multi-step prediction scenario. To address this issue, this paper proposes a sequence-to-sequence Chrono-initialized long short-term memory (S2S-CLSTM), which can take into account the dynamic nature of dam displacement lag effect in explaining the nonlinear relationship between displacement and complex external features. Specifically, we redefine LSTM initialization using the Chrono initializer and construct a sequence-to-sequence model (S2S-CLSTM) based on the Chrono-initialized Long shortterm memory network (CLSTM). CLSTM adapts to dynamic displacement lag effect by incorporating temporal dependency information in implicit parameters, enhancing model generalization. The S2S paradigm aids in maintaining robustness while interpreting dam displacements across different time scales. Secondly, the study introduce a special Re-optimization strategy tailored for S2S-CLSTM to mitigate performance degradation caused by ambiguous definitions of displacement lag extents. Using monitoring data from a real arch dam, the effectiveness of model and method is verified. Within the prediction step range of 3 to 7, the S2S-CLSTM achieves an impressive average R2 of 0.764, with MAE and RMSE values of only 0.623 mm and 0.797 mm, respectively. In addition, this work also explores the influence of the dam section location on the displacement lag effect model to emphasize the importance of the proposed methods in dam displacement multi-step prediction.
Keyword ：
Chrono-initialized Long short-term memory network Chrono-initialized Long short-term memory network Dam displacement multi-step prediction Dam displacement multi-step prediction Deep learning Deep learning Time lag effect Time lag effect
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Yan , Fu, Jiayuan , Lin, Chuan et al. A novel deep learning multi-step prediction model for dam displacement using Chrono-initialized LSTM and sequence-to-sequence framework [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 271 . |
| MLA | Su, Yan et al. "A novel deep learning multi-step prediction model for dam displacement using Chrono-initialized LSTM and sequence-to-sequence framework" . | EXPERT SYSTEMS WITH APPLICATIONS 271 (2025) . |
| APA | Su, Yan , Fu, Jiayuan , Lin, Chuan , Lai, Xiaohe , Zheng, Zhiming , Lin, Youlong et al. A novel deep learning multi-step prediction model for dam displacement using Chrono-initialized LSTM and sequence-to-sequence framework . | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 271 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In a coastal ecological project aimed at wave attenuation through mangroves, incorporating oyster reefs as a complementary component to establish an "oyster reefs + mangrove" wave attenuation system could enhance the survival probability of mangroves, as well as improve the overall effectiveness of wave attenuation. This study investigates and proposes an innovative wave attenuation system consisting of oyster reefs and mangroves with various configurations. Laboratory experiments were conducted in a wave flume using artificial models of mangroves and oyster reefs to examine the impact of the system on wave attenuation, thereby providing a scientific foundation for coastal ecological restoration projects. The findings demonstrate that the wave attenuation coefficient exhibited a positive correlation with both the significant wave height and oyster reef height, as well as with mangrove density. Conversely, it displayed a negative association with water depth and period. Notably, oyster reefs substantially affected the wave attenuation. When three layers of oyster reefs are integrated with staggered dense mangroves, the system demonstrates optimal wave attenuation, with coefficients ranging from 0.38 to 0.42. The incorporation of oyster reefs within mangroves significantly enhances the capacity of wave attenuation, resulting in an increase of up to 0.26 in the wave attenuation coefficient. Moreover, although the combined wave attenuation coefficient of the individual mangroves and oyster reefs was higher than that of the system, the system's overall wave attenuation surpassed that of either component. A theoretical equation has been formulated to quantify wave attenuation in the oyster reefs-mangrove system, aiming to provide practical guidance for coastal restoration projects. Maximizing the height of oyster reefs in areas with low water depth and pairing them with staggered dense mangroves is recommended to reduce wave energy in coastal restoration projects. The most effective wave reduction strategy for areas with high water depth is a combination of tall oyster reefs and staggered or in-line clusters of dense mangroves.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jiang, Beihan , Fu, Chenming , You, Tuofu et al. A laboratory study on wave Attenuation by oyster reefs-mangrove system [J]. | GEO-MARINE LETTERS , 2025 , 45 (1) . |
| MLA | Jiang, Beihan et al. "A laboratory study on wave Attenuation by oyster reefs-mangrove system" . | GEO-MARINE LETTERS 45 . 1 (2025) . |
| APA | Jiang, Beihan , Fu, Chenming , You, Tuofu , Sun, Yuanmin , Lai, Xiaohe , Cai, Feng et al. A laboratory study on wave Attenuation by oyster reefs-mangrove system . | GEO-MARINE LETTERS , 2025 , 45 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
考虑到滑坡编录制作的耗时性,建立一种"可迁移"的滑坡易发性模型已越发重要.合理利用现有完整滑坡数据地区的样本集对无样本区域进行易发性预测具有重要意义.运用迁移成分分析(transfer component analysis,TCA)方法,结合深度学习卷积神经网络(convolutional neural network,CNN),尝试引入一种基于迁移学习域自适应方法的TCA-CNN模型,并以福建省两个库岸地区为例,提取 11个库岸相关环境因子建立滑坡空间数据库,将有样本的池潭库区易发性模型迁移至无样本的棉花滩库区进行预测,实现跨区域滑坡易发性评价.通过对棉花滩库区进行易发性预测,结果显示:(1)采用TCA方法处理后的不同研究区数据最大均值差异(maximize mean discrepancy,MMD)明显降低(0.022),数据实现近似同分布;(2)TCA-CNN模型的跨区域预测精度为 0.854,高于CNN模型(0.791),且通过历史滑坡验证其落入高、极高易发性区间的滑坡频率比占比最高(89.1%);(3)受试者工作特性(receiver operating characteristic,ROC)曲线下面积TCA-CNN模型为 0.93,高于CNN模型的 0.90.可见TCA-CNN模型能够有效运用建模区的样本数据实现对无样本区域的易发性评价,且相比于传统机器模型在进行跨区域预测时具有更高、更稳定的预测准确率,具备更强的泛化能力.
Keyword ：
卷积神经网络 卷积神经网络 库岸边坡 库岸边坡 数据缺失 数据缺失 滑坡 滑坡 滑坡易发性 滑坡易发性 灾害 灾害 迁移成分分析 迁移成分分析
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 苏燕 , 黄绍翔 , 赖晓鹤 et al. 基于迁移成分分析的库岸跨区域滑坡易发性评价 [J]. | 地球科学 , 2024 , 49 (5) : 1636-1653 . |
| MLA | 苏燕 et al. "基于迁移成分分析的库岸跨区域滑坡易发性评价" . | 地球科学 49 . 5 (2024) : 1636-1653 . |
| APA | 苏燕 , 黄绍翔 , 赖晓鹤 , 陈耀鑫 , 杨凌鋆 , 林川 et al. 基于迁移成分分析的库岸跨区域滑坡易发性评价 . | 地球科学 , 2024 , 49 (5) , 1636-1653 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
It is crucial to create a 'migratable' landslide susceptibility model considering the time-consuming process of recording landslides. However, a sample set of all known landslide data areas must be used in forecasting the susceptibility of unsampled regions adequately. In this paper, we attempt to develop a TCA-CNN model to enable trans-regional landslide susceptibility evaluation, which is based on the adaption domain of transfer learning by integrating the transfer component analysis (TCA) with deep learning convolutional neural network (CNN). The spatial database of landslides is constructed by extracting 11 environmental factors of the reservoir bank area, then the Mianhuatan reservoir area without samples is then predicted using the susceptibility model from the Chitan reservoir area with samples. The results show that: (1) The maximum mean discrepancy (MMD) of data from different study areas treated by TCA decreased significantly (0.022), and the data is approximately identically distributed; (2) The trans-regional prediction accuracy by the TCA-CNN model is 0.854, which is higher than that of the CNN model (0.791). And it can be verified that the proportion of landslide frequency falling into the high/extremely-high susceptibility interval is the highest (89.1%) in the historical landslide; (3) The area under the receiver operating characteristic (ROC) curve of the TCA-CNN model is 0.93, which is higher than that of the CNN model (0.90). It’s obvious that the TCA-CNN model can effectively use the samples data of the modeling area to realize the susceptibility evaluation of the unsampled area. Compared with the traditional machine model, TCA-CNN model has higher and more stable prediction accuracy and stronger generalization ability in cross-region prediction. © 2024 China University of Geosciences. All rights reserved.
Keyword ：
Convolution Convolution Convolutional neural networks Convolutional neural networks Deep learning Deep learning Forecasting Forecasting Landslides Landslides Neural network models Neural network models Transfer learning Transfer learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Yan , Huang, Shaoxiang , Lai, Xiaohe et al. Evaluation of Trans⁃Regional Landslide Susceptibility of Reservoir Bank Based on Transfer Component Analysis [J]. | Earth Science - Journal of China University of Geosciences , 2024 , 49 (5) : 1636-1653 . |
| MLA | Su, Yan et al. "Evaluation of Trans⁃Regional Landslide Susceptibility of Reservoir Bank Based on Transfer Component Analysis" . | Earth Science - Journal of China University of Geosciences 49 . 5 (2024) : 1636-1653 . |
| APA | Su, Yan , Huang, Shaoxiang , Lai, Xiaohe , Chen, Yaoxin , Yang, Lingjun , Lin, Chuan et al. Evaluation of Trans⁃Regional Landslide Susceptibility of Reservoir Bank Based on Transfer Component Analysis . | Earth Science - Journal of China University of Geosciences , 2024 , 49 (5) , 1636-1653 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Given the time-consuming nature of compiling landslide inventories, it is increasingly important to develop transferable landslide susceptibility models that can be applied to regions without existing data. In this study, we propose a feature-based domain adaptation method to improve the transferability of landslide susceptibility models, especially in "no sample" areas. Two typical landslide-prone areas in Fujian province, southeastern China, were chosen as research cases to test the practicality of the transfer effect. Five conventional machine learning algorithms (Support vector machines (SVM), Random Forest (RF), Logistic Regression (LOG), K-nearest neighbor (KNN), and Decision tree (C4.5)) are used to model landslide susceptibility in sampled areas (source domain), and a feature transfer-based landslide susceptibility evaluation model is constructed under coupled feature transfer methods to evaluate the susceptibility of landslide in un-sampled areas (target domain). The results showed that feature transfer can effectively improve the transferability of different machine learning models for cross-regional prediction (The indicators have improved overall by 8.49%), with SVM (increased by 13.68%) and LOG (increased by 10.19%) models showing the most significant improvements. The feature-based domain adaptive method can alleviate the burden of collecting and labeling new data, and effectively improve the assessment performance of machine learning-based landslide susceptibility models in un-sampled areas. This is a new solution for landslide susceptibility assessment in completely "no sample" areas. (c) 2024 International Association for Gondwana Research. Published by Elsevier B.V. All rights reserved.
Keyword ：
Data scarcity Data scarcity Feature domain adaptation Feature domain adaptation Landslide susceptibility Landslide susceptibility Machine learning Machine learning Reservoir bank slope Reservoir bank slope
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Yan , Chen, Yaoxin , Lai, Xiaohe et al. Feature adaptation for landslide susceptibility assessment in "no sample" areas [J]. | GONDWANA RESEARCH , 2024 , 131 : 1-17 . |
| MLA | Su, Yan et al. "Feature adaptation for landslide susceptibility assessment in "no sample" areas" . | GONDWANA RESEARCH 131 (2024) : 1-17 . |
| APA | Su, Yan , Chen, Yaoxin , Lai, Xiaohe , Huang, Shaoxiang , Lin, Chuan , Xie, Xiudong . Feature adaptation for landslide susceptibility assessment in "no sample" areas . | GONDWANA RESEARCH , 2024 , 131 , 1-17 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Detecting water head is crucial in groundwater utilization, and requires quick and accurate solutions. This study employs a method combining the collocation Trefftz method (CTM) and the fictitious time integration method (FTIM) for groundwater head detection and restoration. The Laplace equation is solved using CTM, and the Trefftz basis function is linearly combined to fit the exact solution while adding characteristics length for numerical stability. The FTIM solves the nonlinear algebraic equations system for water head detection. Numerical examples quantify the method's accuracy, and boundary restoration results are compared with the Picard successive approximation method, showcasing FTIM's advantages in convergence steps and precision. The solution comparison under irregular boundary conditions further verifies the proposed method's efficacy (MAE <= 10-15). The CTM-FTIM calculated water level boundary aligns with the actual boundary, and its noise immunity is verified using real observation well data (MAE <= 10-2, Itertimes <= 5000). The CTM-FTIM method eliminates meshing needs for quick solutions in irregular regions, accurately determining water levels in the study domain using few known boundary points, solving infinite domain groundwater head detection.
Keyword ：
Fictitious time integration method Fictitious time integration method Groundwater head detection recovery Groundwater head detection recovery Noise immunity Noise immunity Observation well data Observation well data Trefftz method Trefftz method
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Yan , Huang, Bin , Yang, Lingjun et al. Study on the detection of groundwater boundary based on the Trefftz method [J]. | NATURAL HAZARDS , 2024 , 120 (8) : 8057-8085 . |
| MLA | Su, Yan et al. "Study on the detection of groundwater boundary based on the Trefftz method" . | NATURAL HAZARDS 120 . 8 (2024) : 8057-8085 . |
| APA | Su, Yan , Huang, Bin , Yang, Lingjun , Lai, Xiaohe , Lin, Chuan , Xie, Xiudong et al. Study on the detection of groundwater boundary based on the Trefftz method . | NATURAL HAZARDS , 2024 , 120 (8) , 8057-8085 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Water discharge and sediment load are often controlled by a combination of factors. However, the relationship between water and sediment load changes and meteorological oscillations has rarely been explored for different river sizes. Explanations for the various responses of water-sediment changes to meteorological factors in different rivers is important for understanding global hydrology. In this study, we analyzed data from 2002-2022 using cross-wavelet and wavelet coherence in an attempt to characterize the effects of large-scale climatic oscillations on 10 rivers in eastern China. Comparing the results shows that water releases lag three months or more behind SST variations. It also oscillates interannually (mostly every 8-16 months). Most rivers runoff lags changes in PDO by three months or more. The impact of ENSO (El Ni & ntilde;o-Southern Oscillation) on each river basin gradually decreases from south to north. The impacts on northern rivers such as the Yellow River, Huai Riverand Liao River are weaker. At the same time, the water discharge changes in the Pearl River and Minjiang River basins in southeastern China are extremely rapid and sensitive to ENSO events. Meanwhile, the impacts of ENSO on large rivers lasted throughout the study period, while the impacts of ENSO on smaller rivers had intermittent periods, and the response rates of geographically similar mountain and stream-type rivers were not the same. The effect of the PDO (Pacific Decadal Oscillation) warm and cold phases was different for each region. Our research contributes to understanding the relationship between rivers and climate oscillations, advancing Water-Sediment Balance and Global Sustainability-key goals of the United Nations 2030 Agenda for Sustainable Development.
Keyword ：
climate oscillations climate oscillations ENSO ENSO hydrological variability hydrological variability PDO PDO wavelet transform wavelet transform
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Feng , Zhang, Li , Zhong, Yaozhao et al. Linkage detection between climate oscillations and water and sediment discharge of 10 rivers in Eastern China [J]. | FRONTIERS IN MARINE SCIENCE , 2024 , 11 . |
| MLA | Zhang, Feng et al. "Linkage detection between climate oscillations and water and sediment discharge of 10 rivers in Eastern China" . | FRONTIERS IN MARINE SCIENCE 11 (2024) . |
| APA | Zhang, Feng , Zhang, Li , Zhong, Yaozhao , Zou, Huangjie , Lai, Xiaohe , Xie, Yanshuang . Linkage detection between climate oscillations and water and sediment discharge of 10 rivers in Eastern China . | FRONTIERS IN MARINE SCIENCE , 2024 , 11 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
To investigate the patterns of wave pressure exerted on the superstructure and substructure of offshore boxgirder bridges under the influence of tsunamis, a scale model of 1:25 for both the pier-girder and pier model was constructed for tsunami wave impact testing. The study examined pressure and flow field characteristics at various locations on the box girders and piers under different tsunami wave conditions, analyzing the interaction and mechanisms of tsunami impact pressures between the girders and piers, as well as the effect of impact submersion coefficients on these pressures. The findings indicate significant variations in the degree to which different parts of the box girder are affected, with notably higher pressure at the Girder-Pier Connection (GPC) of the girder's bottom compared to other areas, reaching a differential of 16%. Under conditions where the pier is not submerged, the peak pressure at the top of the pier in the pier-girder model was found to be 40% higher than in the pier-only model. Therefore, ignoring the interaction between girders and piers can lead to an underestimation of the pressures caused by tsunami waves. This research is crucial for identifying bridge failure modes and developing mitigation and protection measures.
Keyword ：
Flow field characteristics Flow field characteristics Impact submersion coefficients Impact submersion coefficients Offshore box-girder bridges Offshore box-girder bridges Pressure Pressure Tsunami Tsunami
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Anhua , Gu, Yin , Lai, Xiaohe et al. Experimental study on tsunami impact on offshore box-girder bridges [J]. | OCEAN ENGINEERING , 2024 , 314 . |
| MLA | Yu, Anhua et al. "Experimental study on tsunami impact on offshore box-girder bridges" . | OCEAN ENGINEERING 314 (2024) . |
| APA | Yu, Anhua , Gu, Yin , Lai, Xiaohe , Huang, Xinyi . Experimental study on tsunami impact on offshore box-girder bridges . | OCEAN ENGINEERING , 2024 , 314 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
