Multi-resolution reconstruction of longitudinal streambed footprints using embedded sparse convolutional autoencoders
文献类型：期刊论文
| 作者 | Yang, Yifan4; Tang, Zihao3; Shao D(邵东)2; Xu, Zhonghou1 |
| 刊名 | JOURNAL OF HYDROLOGY
 |
| 出版日期 | 2025-06-01 |
| 卷号 | 654页码:18 |
| 关键词 | Machine learning Streambed footprint Convolutional autoencoder Multi-resolution reconstruction |
| ISSN号 | 0022-1694 |
| DOI | 10.1016/j.jhydrol.2025.132852 |
| 通讯作者 | Tang, Zihao(ztan692@aucklanduni.ac.nz) |
| 英文摘要 | This study introduces an embedded convolutional autoencoder (CAE) architecture designed for the multiresolution reconstruction of longitudinal streambed footprints as sparse heatmaps. Three standalone but interrelated CAEs are trained to achieve double-upsampling, enhancing the heatmaps' spatial resolution and data measurement resolution simultaneously. Transfer learning improves model training efficiency by incorporating a trained model into a larger model at the next level. Cascading the CAEs facilitates a direct pathway for enhancing data quality from the coarsest inputs and recovering fine-grained patterns. Systematic evaluations prove the CAEs' reliability in working individually and collectively. Robustness analyses demonstrate the model's ability to retain field reconstructive quality when subjected to various corrupted inputs, including bulk data loss and spiky noise interference with local measurements at different streambed sections. The model's capacity benefitted from including attention mechanisms (convolutional block attention modules, CBAM) and the adaptive training strategy using crafted loss functions, ensuring efficient extraction and learning of sparse dense patterns and fast reconstruction of physically sound fields. The model architecture's flexibility and scalability are highlighted, proving it suitable for more complex geophysical systems with higher dimensions. The proposed embedded CAE architecture provides a foundational tool for creating digital surrogates of river courses and similar entities, which often involve inherently sparsely distributive data in both spatial and temporal domains. |
| 分类号 | 一类 |
| WOS关键词 | RIVER ; PROBABILITY ; MODEL |
| WOS研究方向 | Engineering ; Geology ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001427259700001 |
| 其他责任者 | Tang, Zihao |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/100158]  |
| 专题 | 力学研究所_流固耦合系统力学重点实验室(2012-) |
| 作者单位 | 1.Natl Inst Water & Atmospher Res, Hamilton, New Zealand 2.Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing, Peoples R China; 3.Univ Auckland, Dept Civil & Environm Engn, Auckland, New Zealand; 4.Wuhan Univ, State Key Lab Water Resources Engn & Management, Wuhan, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Yang, Yifan,Tang, Zihao,Shao D,et al. Multi-resolution reconstruction of longitudinal streambed footprints using embedded sparse convolutional autoencoders[J]. JOURNAL OF HYDROLOGY,2025,654:18. |
| APA | Yang, Yifan,Tang, Zihao,邵东,&Xu, Zhonghou.(2025).Multi-resolution reconstruction of longitudinal streambed footprints using embedded sparse convolutional autoencoders.JOURNAL OF HYDROLOGY,654,18. |
| MLA | Yang, Yifan,et al."Multi-resolution reconstruction of longitudinal streambed footprints using embedded sparse convolutional autoencoders".JOURNAL OF HYDROLOGY 654(2025):18. |
入库方式： OAI收割
来源：力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。