GeomorPM: a geomorphic pretrained model integrating convolution and Transformer architectures based on DEM data
文献类型：期刊论文
| 作者 | Yang, Jiaqi3,4; Xu, Jun4; Zhu, Yunqiang2,4; Liu, Ze1,4; Zhou, Chenghu2,4 |
| 刊名 | INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
 |
| 出版日期 | 2024-10-12 |
| 卷号 | N/A |
| 关键词 | Self-supervised learning pretrained model DEM autoencoder geomorphology |
| DOI | 10.1080/13658816.2024.2414409 |
| 产权排序 | 1 |
| 英文摘要 | As the domain of artificial intelligence has advanced, the integration of deep learning techniques into terrain and landform analysis has become more prevalent. Nevertheless, many existing methods are fully supervised and designed for specific tasks; thus, their transferability is limited and massive annotated samples are required. This study introduces a geomorphic pretrained model (GeomorPM) capable of performing multiple tasks. First, an architecture was designed that combined a convolution-based Vector Quantised-Variational Autoencoder (VQVAE) with a Transformer-based masked autoencoder (MAE) framework, allowing it to autonomously learn local details and global patterns from large-scale digital elevation model (DEM) data. Subsequently, GeomorPM, based on the VQMAE architecture, was pretrained on massive DEM data and fine-tuned for three specific tasks: DEM void filling, DEM superresolution, and landform classification. GeomorPM outperformed the traditional and other deep learning methods in all three tasks, demonstrating the superior learning ability and transferability of the model. This study provides a practical framework for developing pretrained models based on DEMs that can be expanded to other continuous geoscientific data. |
| WOS关键词 | IMAGE ; CLASSIFICATION ; NETWORK |
| WOS研究方向 | Computer Science ; Geography ; Physical Geography ; Information Science & Library Science |
| WOS记录号 | WOS:001331028700001 |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/208242]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Xu, Jun |
| 作者单位 | 1.China Univ Geosci Beijing, Sch Informat Engn, Beijing, Peoples R China 2.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing, Peoples R China 3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yang, Jiaqi,Xu, Jun,Zhu, Yunqiang,et al. GeomorPM: a geomorphic pretrained model integrating convolution and Transformer architectures based on DEM data[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2024,N/A. |
| APA | Yang, Jiaqi,Xu, Jun,Zhu, Yunqiang,Liu, Ze,&Zhou, Chenghu.(2024).GeomorPM: a geomorphic pretrained model integrating convolution and Transformer architectures based on DEM data.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,N/A. |
| MLA | Yang, Jiaqi,et al."GeomorPM: a geomorphic pretrained model integrating convolution and Transformer architectures based on DEM data".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE N/A(2024). |
入库方式： OAI收割
来源：地理科学与资源研究所
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。