中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
Adding attention to the neural ordinary differential equation for spatio-temporal prediction

文献类型：期刊论文

作者Wang, Peixiao3,4; Zhang, Tong4; Zhang, Hengcai3; Cheng, Shifen; Wang, Wangshu2
刊名INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
出版日期2023-11-07
关键词Geospatial artificial intelligence spatio-temporal prediction spatio-temporal attention neural ordinary differential equation
DOI10.1080/13658816.2023.2275160
产权排序1
文献子类Article ; Early Access
英文摘要Explainable spatio-temporal prediction gains attraction in the development of geospatial artificial intelligence. The neural ordinal differential equation (NODE) emerges as a new solution for explainable spatio-temporal prediction. However, challenges still need to be solved in most existing NODE-based prediction models, such as difficulty modeling spatial data and mining long-term temporal dependencies in data. In this study, we propose a spatio-temporal attentional NODE (STA-ODE) to address the two challenges above. First, we define a spatio-temporal ordinary differential equation to predict a value at each time iteratively by a novel spatio-temporal derivative network. Second, we develop an attention mechanism to fuse multiple prediction values for capturing long-term temporal dependencies in data. To train the STA-ODE model, we design a loss function that aligns the prediction results in spatial dimension with prediction results in temporal dimension to calibrate the parameters of the model. The proposed model was validated with three real-world spatio-temporal datasets (traffic flow dataset, PM2.5 monitoring dataset, and temperature monitoring dataset). Experimental results showed that STA-ODE outperformed seven existing baselines regarding prediction accuracy. In addition, we used visualization to demonstrate the sound interpretability and prediction accuracy of the STA-ODE model.
WOS关键词URBAN FLOW PREDICTION ; NETWORKS ; INTERPOLATION ; MULTITASK
WOS研究方向Computer Science ; Geography ; Physical Geography ; Information Science & Library Science
WOS记录号WOS:001096818500001
源URL[http://ir.igsnrr.ac.cn/handle/311030/199449]  
专题资源与环境信息系统国家重点实验室_外文论文
作者单位1.Vienna Univ Technol, Dept Geodesy & Geoinformat, Res Unit Cartog, Vienna, Austria
2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China
3.Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan, 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		 Wang, Peixiao,Zhang, Tong,Zhang, Hengcai,et al. Adding attention to the neural ordinary differential equation for spatio-temporal prediction[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2023.
APA Wang, Peixiao,Zhang, Tong,Zhang, Hengcai,Cheng, Shifen,&Wang, Wangshu.(2023).Adding attention to the neural ordinary differential equation for spatio-temporal prediction.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE.
MLA Wang, Peixiao,et al."Adding attention to the neural ordinary differential equation for spatio-temporal prediction".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2023).

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。