Multi-modal spatio-temporal meteorological forecasting with deep neural network | |
Xinbang Zhang2,3; Qizhao Jin2,3; Tingzhao Yu1; Shiming Xiang2,3; Qiuming Kuang1; Véronique Prinet3; Chunhong Pan3 | |
刊名 | ISPRS Journal of Photogrammetry and Remote Sensing |
2022-03 | |
页码 | 14 |
关键词 | Meterological forecasting Deep learning Neural architecture search AutoML |
文献子类 | 已录用未发表 |
英文摘要 | Meteorological forecasting is a typical and fundamental problem in the remote sensing field. Although many brilliant forecasting methods have been developed, long-term (a few days ahead) meteorological prediction still relies on traditional Numerical Weather Prediction (NWP) that is not competent for the oncoming flood of meteorological data. To improve the forecasting ability faced with meteorological big data, this article adopts the Automated Machine Learning (AutoML) technique and proposes a deep learning framework to model the dynamics of multi-modal meteorological data along spatial and temporal dimensions. Spatially, a convolution based network is developed to extract the spatial context of multi-modal meteorological data. Considering the complex relationship between different modalities, the Neural Architecture Search (NAS) technique is introduced to automate the designing procedure of the fusion network in a purely data-driven manner. As for the temporal dimension, an encoder-decoder structure is built to exhaustively model the temporal dynamics of the embedding sequence. Specializing for the numerical sequence representation transformation, the multi-head attention module endows the proposed model with the ability to forecast future data. Generally speaking, the whole framework could be optimized with the standard back-propagation, yielding an end-to-end learning mechanism. To investigate its feasibility, the proposed model is evaluated with four typical meteorological modalities including temperature, relative humidity, and two components of wind, which are all restricted under the region whose latitude and longitude range from to N and E to E, respectively. Experiments on two datasets with different resolutions verify that deep learning is effective as an operational technique for the meteorological forecasting task. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48955] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Shiming Xiang |
作者单位 | 1.The Public Meteorological Service Center, China Meteorological Administration 2.The School of Artificial Intelligence, University of Chinese Academy of Sciences 3.The Department of National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Xinbang Zhang,Qizhao Jin,Tingzhao Yu,et al. Multi-modal spatio-temporal meteorological forecasting with deep neural network[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2022:14. |
APA | Xinbang Zhang.,Qizhao Jin.,Tingzhao Yu.,Shiming Xiang.,Qiuming Kuang.,...&Chunhong Pan.(2022).Multi-modal spatio-temporal meteorological forecasting with deep neural network.ISPRS Journal of Photogrammetry and Remote Sensing,14. |
MLA | Xinbang Zhang,et al."Multi-modal spatio-temporal meteorological forecasting with deep neural network".ISPRS Journal of Photogrammetry and Remote Sensing (2022):14. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论